diff --git a/bf16/model-00001-of-000163.safetensors b/bf16/model-00001-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96405d5df8884d20c97d978e7c1f3101ced0e68d --- /dev/null +++ b/bf16/model-00001-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9689063991e3327db2eda47cc605ca65c89fff310eefeb9a7cac0ed169f3adc1 +size 8603795312 diff --git a/bf16/model-00002-of-000163.safetensors b/bf16/model-00002-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a60926903e04ca93a1c04c3afc40057b811c0bb5 --- /dev/null +++ b/bf16/model-00002-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da297ec9d792bad3c4796a4a7ae5749e06bc5792a7f37c05548a6579ba5c53b0 +size 8602553944 diff --git a/bf16/model-00003-of-000163.safetensors b/bf16/model-00003-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bb07644a450d753fa5499c14d42a9ab95782e33 --- /dev/null +++ b/bf16/model-00003-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da1d2b328ca326dab29e4618ab6426bd2e4b8e0ffaf244d2ffc7ee9a5827d30e +size 8602554152 diff --git a/bf16/model-00004-of-000163.safetensors b/bf16/model-00004-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d05b55bd74149c529ced2e592ae1e3a0f1c3b1e --- /dev/null +++ b/bf16/model-00004-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a17977cd8eb1caea2b67ce6316918464f82f500982b5a39675b9a0c7ecdcf80 +size 8597378736 diff --git a/bf16/model-00005-of-000163.safetensors b/bf16/model-00005-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0efc73c5d21bf73a370104afb39555f3497631d --- /dev/null +++ b/bf16/model-00005-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62690a06fe52986037446bda5d227fc2ff22db705da6d5338f6d53845b5eff61 +size 8602554040 diff --git a/bf16/model-00006-of-000163.safetensors b/bf16/model-00006-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..301faec3a762f0cdd14e6f2a8ac0bfd926ef6dac --- /dev/null +++ b/bf16/model-00006-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc98b77d3e60eb98092030b35b5308bc5bdda5bcfe7b187273f10244df283354 +size 8612055008 diff --git a/bf16/model-00007-of-000163.safetensors b/bf16/model-00007-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f9cec2c81377ccc1e06fa7ffa0adfdf98a06818 --- /dev/null +++ b/bf16/model-00007-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44763eae1978da9253a53435128903f28916eb4d7c81527a4e70d5eefb103ea5 +size 8617238032 diff --git a/bf16/model-00008-of-000163.safetensors b/bf16/model-00008-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ca6c297f0524fd7b82ccc02ca242131e7e46337 --- /dev/null +++ b/bf16/model-00008-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbc32854fd7ef25839b185e7a046aea767812acb704056007088211122fe4ac2 +size 8602554136 diff --git a/bf16/model-00009-of-000163.safetensors b/bf16/model-00009-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a59b0f46fbe27d4c1dc3766b9ebfc9f7cb45cf22 --- /dev/null +++ b/bf16/model-00009-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a14494a5e968caa17c592fb5e5cb0c1b68a530d8f6284db94e1fdad292aed49 +size 8597378840 diff --git a/bf16/model-00010-of-000163.safetensors b/bf16/model-00010-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74b8e178182528b17b4411502d310ae2265b3fa7 --- /dev/null +++ b/bf16/model-00010-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9455ccd9e3aa141943b5162d5821ff31670a96c4ecac14f39bd29401c9bab7 +size 8602553936 diff --git a/bf16/model-00011-of-000163.safetensors b/bf16/model-00011-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eae9e4744199a1be82516491da96c706bf60fda4 --- /dev/null +++ b/bf16/model-00011-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b521f38e4ba3086e79eb42dcd45446de6c039b37c825f04cd393e1721512a7 +size 8602554160 diff --git a/bf16/model-00012-of-000163.safetensors b/bf16/model-00012-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e996da3cc463f1c74da118cfb6d8a31a4b834aaf --- /dev/null +++ b/bf16/model-00012-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d4055de0379fe5d067e5fcf48e633cfb032d06e615ee3991dd6a86fd71f2f1f +size 2965443072 diff --git a/bf16/model-00013-of-000163.safetensors b/bf16/model-00013-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c66d2dddd8c28c63206229c86a74b7b977e85ca7 --- /dev/null +++ b/bf16/model-00013-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcfce460d5b80d1f0e8f8f8ef26f65cec16321127e0c9b26b7019cc5c43fef35 +size 8597321080 diff --git a/bf16/model-00014-of-000163.safetensors b/bf16/model-00014-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a3b8ba35cf78c0e1628f493c99cb3e7ce858bc7a --- /dev/null +++ b/bf16/model-00014-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c0c8c667b8e6def0a7c7f8c1e93b0de0a675dfdaf55745678c591017e50813 +size 8602554128 diff --git a/bf16/model-00015-of-000163.safetensors b/bf16/model-00015-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e4c05508ca2cf211d63014924026043a8cec88d --- /dev/null +++ b/bf16/model-00015-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dabd665d53de21470129610ba1fea76872ceba02b0fa24a2fd3dacd82f45aaa8 +size 8597378840 diff --git a/bf16/model-00016-of-000163.safetensors b/bf16/model-00016-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe587dbd17c3786802a8ce819687b98f1a5dd343 --- /dev/null +++ b/bf16/model-00016-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61deabfc8b196d3f03f05da180696cb3b0e26daca13434b8f6b88aac47c5bd27 +size 8602553936 diff --git a/bf16/model-00017-of-000163.safetensors b/bf16/model-00017-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a97880903da69cf0325f021ae303fa706fe05f0e --- /dev/null +++ b/bf16/model-00017-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c350fcb049f02811825e4d3aaeb0ccbfcf7afc56f0ceab9f19eb87844d08d5 +size 8602554152 diff --git a/bf16/model-00018-of-000163.safetensors b/bf16/model-00018-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2151926348a922a4019dde4fa4243a1b620eb9d4 --- /dev/null +++ b/bf16/model-00018-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1004c980cd6ca691b77fb432c43b6478b39c91fce8f355a1371befe48757c492 +size 8597378744 diff --git a/bf16/model-00019-of-000163.safetensors b/bf16/model-00019-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0aeacf8d6161acd2701c9cbf4c3ac02c7b11c9e1 --- /dev/null +++ b/bf16/model-00019-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8a9df0a3c0c19b9b01b5493f15767d7ec0d6d358652287b40460279630d7f7 +size 8602554024 diff --git a/bf16/model-00020-of-000163.safetensors b/bf16/model-00020-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95ce0918d436b7e5eedb0a664ee92150b630f628 --- /dev/null +++ b/bf16/model-00020-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407310d086bd709e20bce0a0f385147d8e7df5f016a34dcd6ec6cf6bbbb52031 +size 8602554160 diff --git a/bf16/model-00021-of-000163.safetensors b/bf16/model-00021-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ef0ecf451e01fdc519ed412dd3b3e68323ef2390 --- /dev/null +++ b/bf16/model-00021-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181c37a5fda5b2ced5a15b48e46e18c8705cd4f5c1c9a8d5e588e54fe6f7e82c +size 8597378928 diff --git a/bf16/model-00022-of-000163.safetensors b/bf16/model-00022-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2ed36f7b613f9e1877a78be2f5a60073a5cd5fd --- /dev/null +++ b/bf16/model-00022-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9efddafd11c682ed62d98fb20d2b2436e185ea0df685535c05f3a6f374a0d7d8 +size 8602554416 diff --git a/bf16/model-00023-of-000163.safetensors b/bf16/model-00023-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e574969e1d4f34bc04a10e2f1effe5347b9fc5d2 --- /dev/null +++ b/bf16/model-00023-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c2b8296a4745f62f784efda615d16463de4f052ee532590e17decc51327f7c +size 8597379144 diff --git a/bf16/model-00024-of-000163.safetensors b/bf16/model-00024-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f048e416693bc1539e7daba560d4d52e1cc1842 --- /dev/null +++ b/bf16/model-00024-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:938e82e031282d5b7e515949f6696294f51221c8f2775c155c913c1c1b156090 +size 8602554216 diff --git a/bf16/model-00025-of-000163.safetensors b/bf16/model-00025-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f4d81c1a9338abc10bf76d9f12c949d16e597210 --- /dev/null +++ b/bf16/model-00025-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d5aa7deb5b99fa110e44230ddab27220688a4d22f4c70f2f0f44b22faa2c70e +size 8602554448 diff --git a/bf16/model-00026-of-000163.safetensors b/bf16/model-00026-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..469d6378c58d3a4fbb8fadb221cb1fbab9c4522a --- /dev/null +++ b/bf16/model-00026-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f461c42bae462aac737a774ecd32fda2766d54a14785e16dc252ed460077fc +size 8597379056 diff --git a/bf16/model-00027-of-000163.safetensors b/bf16/model-00027-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5d8b97c6d6b71b55722ad2f7ed87cde2e0c3d50 --- /dev/null +++ b/bf16/model-00027-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1f0ff3d55316aaf4f540b0c548a651da4e9d61a45e1edbede9e61d7572daa2 +size 8602554312 diff --git a/bf16/model-00028-of-000163.safetensors b/bf16/model-00028-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc601b41c24bfd63698b9b143276a6c300b9d1c3 --- /dev/null +++ b/bf16/model-00028-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c588e813e5ee482a319e8dceb6555912c2153cf7067075fb03f5a8ff5ee3edab +size 8602554448 diff --git a/bf16/model-00029-of-000163.safetensors b/bf16/model-00029-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e01048aa3738ad58c45b168cacec806bd2800e2b --- /dev/null +++ b/bf16/model-00029-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a582f181b07b1bd98ab334dfc76d810f3b80ecb17074d7956d74dcb151f292d +size 8597378960 diff --git a/bf16/model-00030-of-000163.safetensors b/bf16/model-00030-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18edcc370ad9978c18afb008f03a4297010a4b0c --- /dev/null +++ b/bf16/model-00030-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47e92e133bcc5c0d5fba1431dae37b7b74e105a6b93dbf3e77161f96509a87ed +size 8602554408 diff --git a/bf16/model-00031-of-000163.safetensors b/bf16/model-00031-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..daeba584d057c8635dc1ab91d8cb7f58be7b0005 --- /dev/null +++ b/bf16/model-00031-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f70bcf3fd96ad51270adbc9f5cff5e2bc78f4dd9e5aff3067212d2084e89f84 +size 8597379160 diff --git a/bf16/model-00032-of-000163.safetensors b/bf16/model-00032-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..118fa3fdaab73fe058ec1553594eca9112e43a7b --- /dev/null +++ b/bf16/model-00032-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbea941280267dca29ae701d7b62fd2aca3dbfe75c19073d9acec52fbf52def2 +size 8602554200 diff --git a/bf16/model-00033-of-000163.safetensors b/bf16/model-00033-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a146c4238c5609f7454301a131cab4ad0bba2d63 --- /dev/null +++ b/bf16/model-00033-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50ab567eeca47e48525edc5fb0d78218c127809713c64110a5bc8c936b910edb +size 8602554448 diff --git a/bf16/model-00034-of-000163.safetensors b/bf16/model-00034-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..90c6435193f7ea9ae84c1346b19fbe5998291ca8 --- /dev/null +++ b/bf16/model-00034-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e74ef048d68e26baf50b74f6f19ece672b8a535d4c7dc8697f6d319ccc8a0eb +size 3728809784 diff --git a/bf16/model-00035-of-000163.safetensors b/bf16/model-00035-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2549c0c0164e69a9a4f9a8a3911de63263683892 --- /dev/null +++ b/bf16/model-00035-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3797030ecd4589625c56f99bb074a72ee2514da3531abc0f4a7cdbf390c59b55 +size 8597321376 diff --git a/bf16/model-00036-of-000163.safetensors b/bf16/model-00036-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..49b31baf87850771b66a7ad6626601f3e71679a8 --- /dev/null +++ b/bf16/model-00036-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1e61542a2aa034b0bb755e990e7e8e8b8ef60ecce2a8779e5ea212d953b2f4e +size 8602554424 diff --git a/bf16/model-00037-of-000163.safetensors b/bf16/model-00037-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..adb7b571889e47587fa3973ec295f814c48b8f30 --- /dev/null +++ b/bf16/model-00037-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba03d5bb713ac19ce1a034ac2a997c0e4870ed78945453978cc308a9d4b7cb56 +size 8597379136 diff --git a/bf16/model-00038-of-000163.safetensors b/bf16/model-00038-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b0bb03cdc196e11a4904b4e6200ae6645a636b46 --- /dev/null +++ b/bf16/model-00038-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85650982f01833ff852e04b06c4bcee1d0adb0007c56cfa9348e75dca6609be9 +size 8602554224 diff --git a/bf16/model-00039-of-000163.safetensors b/bf16/model-00039-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..68eb344edce938c5329905fe4c21b17b1a3d5a05 --- /dev/null +++ b/bf16/model-00039-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeffdf24a29567054e8bd8d66714ef8d06eeeb404aba23b3f3e1a2e64a835220 +size 8602554448 diff --git a/bf16/model-00040-of-000163.safetensors b/bf16/model-00040-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7f59d3594865c93cdc6bb0cede739f9b018e49e --- /dev/null +++ b/bf16/model-00040-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571451ba3f066009ba0fa73cb8d091ea235e6e921a2bdc048e1e62fdf5fccf27 +size 8597379040 diff --git a/bf16/model-00041-of-000163.safetensors b/bf16/model-00041-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85a00e9838ca3f762ab4108953277f9e4a2b6eb5 --- /dev/null +++ b/bf16/model-00041-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f0f57aa18f3f87af03e8c1b5497ce01e1271ccc94e4bf2d3ea9eee72a679c8 +size 8602554320 diff --git a/bf16/model-00042-of-000163.safetensors b/bf16/model-00042-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06c63d4d7598e1ad25000d257bf1370b44e3484d --- /dev/null +++ b/bf16/model-00042-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ab984c785dd6e20d19f8e355817240f5bf850d175beb7d0a0e2fad3fa4485a +size 8602554448 diff --git a/bf16/model-00043-of-000163.safetensors b/bf16/model-00043-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99211eb0e49c9450c87e8a5f92ab12a57f65b432 --- /dev/null +++ b/bf16/model-00043-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843a82b64a7e40d0eae33bc05351716915c5e87c035cde75904b4bcb89b93966 +size 8597378944 diff --git a/bf16/model-00044-of-000163.safetensors b/bf16/model-00044-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e3bdedd51c91a4ed059896062bcbcb9587d27c3 --- /dev/null +++ b/bf16/model-00044-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e91b6f50fbd957634461dd2ab69f0a66c2572566c2b568e14c1381ac81b754c +size 8602554416 diff --git a/bf16/model-00045-of-000163.safetensors b/bf16/model-00045-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e50df4f359c64a4d1fd328901cf31e279863e3b --- /dev/null +++ b/bf16/model-00045-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9321ea9d636b025d715fa250a9b03f02375a69a8ec83b6a30f9a0ed6a83090c7 +size 8597379144 diff --git a/bf16/model-00046-of-000163.safetensors b/bf16/model-00046-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5a12b6a6af6f63e90e5ab8d334ad5ef10c89a10 --- /dev/null +++ b/bf16/model-00046-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a40c98807bdcf9936352f789add4aba380d5455a2df5272307071111d3b0e4b +size 8602554216 diff --git a/bf16/model-00047-of-000163.safetensors b/bf16/model-00047-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af593ca27ce13b76bd655ea5f0542151b8ff31f4 --- /dev/null +++ b/bf16/model-00047-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83bbd3fb06dfaec94e203b166e434c69c1ad7e70bf920c71512cc900c1facdd +size 8602554448 diff --git a/bf16/model-00048-of-000163.safetensors b/bf16/model-00048-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e0e1a03108d5731d0147a3590fd3b12841d1adf --- /dev/null +++ b/bf16/model-00048-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8d07ba69329c49b54082c0bcc51ab7f3d0d44fd1df798aee97664dde02998f +size 8597379056 diff --git a/bf16/model-00049-of-000163.safetensors b/bf16/model-00049-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..669ecd9aae50e6bfcfa13f27c1664bb8865d8abe --- /dev/null +++ b/bf16/model-00049-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f146bdd8f3955426077c00d21742d37995a413231a5962d4121fbc81fd6680e9 +size 8602554312 diff --git a/bf16/model-00050-of-000163.safetensors b/bf16/model-00050-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b76f8198e0f60ea024b26b399d5a1df41daf8625 --- /dev/null +++ b/bf16/model-00050-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79fcf33b868b8b36c3225342522728968a79e79fc2ce3a9dde06a8b80370372b +size 8602554448 diff --git a/bf16/model-00051-of-000163.safetensors b/bf16/model-00051-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b122834d74e72d2bd26deef66ebc4407401b735b --- /dev/null +++ b/bf16/model-00051-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:532ab6ca54495c39ac4a8269f7ad413f18c9d41f4ab65eb27e663e768766bf69 +size 8597378960 diff --git a/bf16/model-00052-of-000163.safetensors b/bf16/model-00052-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ecbf701c4f49c1891a1ad7a41cdf9e5f59e304f5 --- /dev/null +++ b/bf16/model-00052-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5013711c7a3101ce09bcde832f2f36751fb21bca125060252c4985094d71d4 +size 8602554408 diff --git a/bf16/model-00053-of-000163.safetensors b/bf16/model-00053-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a7f1875459f274dc5c2ff280d5073806ed639cd --- /dev/null +++ b/bf16/model-00053-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c106c37d3a440bd83ea7cf4e421e5a8ed757ed3162fb0f7656c03f2cc8dcdd +size 8597379160 diff --git a/bf16/model-00054-of-000163.safetensors b/bf16/model-00054-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b8f4434b6a66ac1679193fbcaef4eaa495f8431 --- /dev/null +++ b/bf16/model-00054-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab1a277adab1ea68c04e88490515bbf3f6f1e1656fa6b87adcabb78878690b4 +size 8602554200 diff --git a/bf16/model-00055-of-000163.safetensors b/bf16/model-00055-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1418f0f57c2dbd9ef225bade8b3a3258b7cbd249 --- /dev/null +++ b/bf16/model-00055-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623479c67db980e3a31cc8d43758eb61b28076a11905df641556d4d126acf241 +size 8602554448 diff --git a/bf16/model-00056-of-000163.safetensors b/bf16/model-00056-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac51009358f7ff409503cef216f9b0004de16726 --- /dev/null +++ b/bf16/model-00056-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15307377d70dc557d51617703be037e9e871e6233d232471a3080ae0d575836 +size 3728809784 diff --git a/bf16/model-00057-of-000163.safetensors b/bf16/model-00057-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..024230605d725867f461406489ccae377331ca70 --- /dev/null +++ b/bf16/model-00057-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177d3985425f628a2e25553c28cd38ad072dd2d7dd0da711d9342082f3895236 +size 8597321376 diff --git a/bf16/model-00058-of-000163.safetensors b/bf16/model-00058-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6989363f4a9e3ed92dbc8d40397e8d5a96330bff --- /dev/null +++ b/bf16/model-00058-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8270ccc646b1141adb6aa9a82651d9d799d12f4225d354a6db16ef34ce8f3edf +size 8602554424 diff --git a/bf16/model-00059-of-000163.safetensors b/bf16/model-00059-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42187191203067f3fa760de9bd05027aa7250d69 --- /dev/null +++ b/bf16/model-00059-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:992204602c0afaf4dea68d15db4bbbde4b302625d6013e5a8013289a851eec19 +size 8597379136 diff --git a/bf16/model-00060-of-000163.safetensors b/bf16/model-00060-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..240e6a31f29adf2e5bf7b9ca772833c13b969e4d --- /dev/null +++ b/bf16/model-00060-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97851a4147e03a96875385385b1c9ba12385f93bf3d6b964a41b2385c1630f47 +size 8602554224 diff --git a/bf16/model-00061-of-000163.safetensors b/bf16/model-00061-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8a57c4865c545b0d21411701fadbb719f20caf3 --- /dev/null +++ b/bf16/model-00061-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd122c96b548af179e0b8bc74c44b6041ad8ea7320f51950d9d60e77db3d798 +size 8602554448 diff --git a/bf16/model-00062-of-000163.safetensors b/bf16/model-00062-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c33dc38e19462f2d316876bfb4ab54e4eb1b53e0 --- /dev/null +++ b/bf16/model-00062-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff37c043b2b06082f0030f7f7a3726af7d56c66ca2aef1269ea1c0704513a6aa +size 8597379040 diff --git a/bf16/model-00063-of-000163.safetensors b/bf16/model-00063-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec1eadebe7b6ebbcf4ba48a9ecc3449ad27eb994 --- /dev/null +++ b/bf16/model-00063-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac114fa970a3bff06bece37d2910bec5f61b27a2e2580f258c05c44deb5513c +size 8602554320 diff --git a/bf16/model-00064-of-000163.safetensors b/bf16/model-00064-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3a6c839a434925f894c9acdab00c302d224201df --- /dev/null +++ b/bf16/model-00064-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f292704808ab84f31676b8834a755eaadc9b39f62788e2f7e81f7fb26fe6d32 +size 8602554448 diff --git a/bf16/model-00065-of-000163.safetensors b/bf16/model-00065-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db1772caeebe7d94264894cbba8dac1dade43504 --- /dev/null +++ b/bf16/model-00065-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eab4764887de8d3289bb1199bd5db47f753ad5fcf3cc2bd2e7e69c747f34c39 +size 8597378944 diff --git a/bf16/model-00066-of-000163.safetensors b/bf16/model-00066-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96bcf0ceebc938b2154a5e224e60ae01d3077fd7 --- /dev/null +++ b/bf16/model-00066-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f1a89a05158b202b66c39bb43e9460e3c97f1e6af047171df5bb64b3c2e3e6 +size 8602554416 diff --git a/bf16/model-00067-of-000163.safetensors b/bf16/model-00067-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2daa9fe5835712c36b190f63727b2395cdefda99 --- /dev/null +++ b/bf16/model-00067-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700c26b73c14831c5329e2be35450b4b8509a3c98f3eaa6b1fc4d38e464f78c2 +size 8597379144 diff --git a/bf16/model-00068-of-000163.safetensors b/bf16/model-00068-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8e0306cb5f33dba4d80138ede192dc2e025a46a --- /dev/null +++ b/bf16/model-00068-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbdc3cca85522b5516c10625d3332c3d77b39532c9a6395648f37befe513b61e +size 8602554216 diff --git a/bf16/model-00069-of-000163.safetensors b/bf16/model-00069-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..278292fbcabcdd72ee6ac5935cf00057d931df6d --- /dev/null +++ b/bf16/model-00069-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b68e9922997dfa96f0c19b92d0e7699535f7c4e1a6c80220ae4ef1a48c1ea2d1 +size 8602554448 diff --git a/bf16/model-00070-of-000163.safetensors b/bf16/model-00070-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61308ccf879b0d8f18fa08c764e5b21fef44829f --- /dev/null +++ b/bf16/model-00070-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ad36bba67d36c0913513dec4465ea446f7bbb62c55816a4aea4e8208514f458 +size 8597379056 diff --git a/bf16/model-00071-of-000163.safetensors b/bf16/model-00071-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5a04a2d266a3ee51acbc10d6476c4261630892b --- /dev/null +++ b/bf16/model-00071-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6cfa6cf1e1fa4d434ed60eb392553de16ad3d02d9fe0952e6bfa50fe1f23909 +size 8602554312 diff --git a/bf16/model-00072-of-000163.safetensors b/bf16/model-00072-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0aefb5b47cbde1155882d21f461ed8f18bb59863 --- /dev/null +++ b/bf16/model-00072-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72c82943105fe86db41ddfef5701178b69567c3908f86924fb8416dbf4d6310 +size 8602554448 diff --git a/bf16/model-00073-of-000163.safetensors b/bf16/model-00073-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc74ef50f49546a2afb490f63a6cff2129dc8b90 --- /dev/null +++ b/bf16/model-00073-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d7d2f95bac595d76529696205c9542373ff63448b7deba3002e317c53037b25 +size 8597378960 diff --git a/bf16/model-00074-of-000163.safetensors b/bf16/model-00074-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..640fae6243f02cdbbb036476c554fe476fac96d9 --- /dev/null +++ b/bf16/model-00074-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07178db960789230023e51e42ea0cc714fbe0ff7710178d6848ba293b430a315 +size 8602554408 diff --git a/bf16/model-00075-of-000163.safetensors b/bf16/model-00075-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d12745f20edd53d48278236933e8530a17275ba8 --- /dev/null +++ b/bf16/model-00075-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ac3a15b671603a4ada7c9c4d3cf7dc1f7e581b0283facaf5ac538615cec0f5 +size 8597379160 diff --git a/bf16/model-00076-of-000163.safetensors b/bf16/model-00076-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c41a1b7da2d7a4c8a42707cc71a5c6e595b1db2 --- /dev/null +++ b/bf16/model-00076-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fa213826d751e39ff72624e36a73207ebc5436c60001555bd52eddd91b7e036 +size 8602554200 diff --git a/bf16/model-00077-of-000163.safetensors b/bf16/model-00077-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7741276208b08ded234147a75e6d6fd76cc0f72d --- /dev/null +++ b/bf16/model-00077-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b553ec9e3a712949c233ff2ae27ce046d9f18249771a39e15e02be6d1f716bf8 +size 8602554448 diff --git a/bf16/model-00078-of-000163.safetensors b/bf16/model-00078-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc9a7bb09488c727a3e467ac8a27f3213c6dc607 --- /dev/null +++ b/bf16/model-00078-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32be473ad68e36b18012e683f2bba1726b382215310f51c5c98a9f585a77565 +size 3728809784 diff --git a/bf16/model-00079-of-000163.safetensors b/bf16/model-00079-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e57a382c6aeb077fdda47f1b9e56374da5f61c01 --- /dev/null +++ b/bf16/model-00079-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdabef32162ba2ce11275fb764636dd21ecd643498a40af50c8c5ef7bf2240a2 +size 8597321376 diff --git a/bf16/model-00080-of-000163.safetensors b/bf16/model-00080-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..01caad0980dc05f849cf5367b5b4ab3fd67ffbd6 --- /dev/null +++ b/bf16/model-00080-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec1b3beba2cea49661872d084cbd3a76243a4fc1b50cf5331a437dd5c2adc0a4 +size 8602554424 diff --git a/bf16/model-00081-of-000163.safetensors b/bf16/model-00081-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb75b4ed868b1601662f9ce50f62a6a7734605bf --- /dev/null +++ b/bf16/model-00081-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34f22c2fed0f954844b25e159e4c5e8314e4846436aca3769133846d6956e9ce +size 8597379136 diff --git a/bf16/model-00082-of-000163.safetensors b/bf16/model-00082-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2ca2bd547a21a833c6b3bc6a93e6b2d380e7504a --- /dev/null +++ b/bf16/model-00082-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49b7d5b2023cdf94016abba3c42413a88ce365124a1fe868e772e573d06db858 +size 8602554224 diff --git a/bf16/model-00083-of-000163.safetensors b/bf16/model-00083-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5616f3de7c9c056d948de9817382c97ec76eefbe --- /dev/null +++ b/bf16/model-00083-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bacf92e4161b095fbe23f948d4f0a0d45c888026fcd97dd72f449e3b908d0465 +size 8602554448 diff --git a/bf16/model-00084-of-000163.safetensors b/bf16/model-00084-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8fdd5fac19b1fa5b6004351d32a39e8172d2948 --- /dev/null +++ b/bf16/model-00084-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b61bbcba489043bdc83ff7c70883f66aed077c20292abe13cc1c04417b81668 +size 8597379040 diff --git a/bf16/model-00085-of-000163.safetensors b/bf16/model-00085-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a54150a719331f6d84214abbd331037da0965319 --- /dev/null +++ b/bf16/model-00085-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e582e58537519b930ba5aff1d12ad7f52118f5e64c8940a58107c3dffdedbfd9 +size 8602554320 diff --git a/bf16/model-00086-of-000163.safetensors b/bf16/model-00086-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5cb8e1a9b317b82a572e43808c114fda2024d138 --- /dev/null +++ b/bf16/model-00086-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd1593c23ca9d56557ca31b6b70cd212790380a990f561b6a079ce57e9e1bc0 +size 8602554448 diff --git a/bf16/model-00087-of-000163.safetensors b/bf16/model-00087-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a8972d77573557c0a809077564af381256a75b8c --- /dev/null +++ b/bf16/model-00087-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33bc261c85e8582d65cb1c68a154e1c6193a78a31eeb0803675ebb93277d23f1 +size 8597378944 diff --git a/bf16/model-00088-of-000163.safetensors b/bf16/model-00088-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2d79f89d1894fdccf4e35eaaa21f9c80e77e187 --- /dev/null +++ b/bf16/model-00088-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a595b5d65948722f88f1ef0ecf58b7193202db8c363282a0d2831c95de485c00 +size 8602554416 diff --git a/bf16/model-00089-of-000163.safetensors b/bf16/model-00089-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f474cbd9c13ad7f7ac10f5ff78c5ffd24c2a965 --- /dev/null +++ b/bf16/model-00089-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176388f886cea6389153da832dc95e57fb4078e41e65c29f5fa6415bcdd0b015 +size 8597379144 diff --git a/bf16/model-00090-of-000163.safetensors b/bf16/model-00090-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..76a0db1fa0eacb18b4e7614b8e0e50e8b55d7745 --- /dev/null +++ b/bf16/model-00090-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:809ba7cd493f8436b0af990b644c33e0ba58cc34a4498b0e4ccc7f1ef11587e2 +size 8602554216 diff --git a/bf16/model-00091-of-000163.safetensors b/bf16/model-00091-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..91baf6abcf79339515252dde5eb9019e7f51c038 --- /dev/null +++ b/bf16/model-00091-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b919e42ff93e99229b3d210d035e826f20ce38ca3618d50c516cd43f6970823d +size 8602554448 diff --git a/bf16/model-00092-of-000163.safetensors b/bf16/model-00092-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9cab6df8b7922a08691a46c7541985564920541 --- /dev/null +++ b/bf16/model-00092-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c49a3d4c5e1a75bbd2051bb8623d4b5bf6e04d7249fdccd386027c99dc00dc55 +size 8597379056 diff --git a/bf16/model-00093-of-000163.safetensors b/bf16/model-00093-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6c5608e9c798abc3ee0df91611b1ae13c9987d41 --- /dev/null +++ b/bf16/model-00093-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed03c6c8544ac6810bedb1c45c4f784d821874b468abf7c459f852fae33e0565 +size 8602554312 diff --git a/bf16/model-00094-of-000163.safetensors b/bf16/model-00094-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..53c446d76aa8c480494c2e7f29280565f4ddbd73 --- /dev/null +++ b/bf16/model-00094-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f81d485bfcc82aba416a18070338c1c66dafbd6800e0f856d892c436e0ee64bf +size 8602554448 diff --git a/bf16/model-00095-of-000163.safetensors b/bf16/model-00095-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7fc8d1898e0ed34ad5fd462f369b6b283bf7334a --- /dev/null +++ b/bf16/model-00095-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada7eb78ee007a0d9596101926a14c230e3a4c0daa7b0c1fdc5b80f177f45914 +size 8597378960 diff --git a/bf16/model-00096-of-000163.safetensors b/bf16/model-00096-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9c7012c3be09a3424b6da2edfdae3182acbc25d2 --- /dev/null +++ b/bf16/model-00096-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f2094573946ff6a217b1b9064fe0539f7999a08aeb35289a9189e23e80c006e +size 8602554408 diff --git a/bf16/model-00097-of-000163.safetensors b/bf16/model-00097-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56900176a5a07c78bca69e1d7afa541da0b79169 --- /dev/null +++ b/bf16/model-00097-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc4237efc8ef71b56c85cd59a5f595e9c8790041c4f7db13a6d62a48d27568d +size 8597379160 diff --git a/bf16/model-00098-of-000163.safetensors b/bf16/model-00098-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a4f49706756652379c4c07399750833cc5f74b9 --- /dev/null +++ b/bf16/model-00098-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77b4be179d197bfe7b52e509956228c0e7faac1fe219d36d521095ed7fcf90e7 +size 8602554200 diff --git a/bf16/model-00099-of-000163.safetensors b/bf16/model-00099-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f63bcb315fe97943bcc6c93b726c2e7f7391f450 --- /dev/null +++ b/bf16/model-00099-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e0e3296f007fe4eac6424cb064139dc1ed3864cde0fa921d07581d4fb6351d5 +size 8602554448 diff --git a/bf16/model-00100-of-000163.safetensors b/bf16/model-00100-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..570968e889d5d328622ae75a55299353ad1711fe --- /dev/null +++ b/bf16/model-00100-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d32f55a31dbd811bc970e8c212deb548e4666ab055724c74e4698a95e984446 +size 3728809784 diff --git a/bf16/model-00101-of-000163.safetensors b/bf16/model-00101-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33e09747cc736e694135b4be22e8be2fcb884da4 --- /dev/null +++ b/bf16/model-00101-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce08a6f24c1f42f0709428fc3508e7d1ef30baae6b7496c29ed94075a6c886f +size 8597321376 diff --git a/bf16/model-00102-of-000163.safetensors b/bf16/model-00102-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0788a20bc2c581a05091ace76a7549950478ad62 --- /dev/null +++ b/bf16/model-00102-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad873e810f45a3ef692f525f962416f02ac13843bf65a6755a75a89aa2ccd43a +size 8602554424 diff --git a/bf16/model-00103-of-000163.safetensors b/bf16/model-00103-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..34e48151c7aca19ca353bc4bb89595387a874952 --- /dev/null +++ b/bf16/model-00103-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6784f52b9e31e5da0389e83dec746c094221471bc2ecf36c1c3553c82231bbe +size 8597379136 diff --git a/bf16/model-00104-of-000163.safetensors b/bf16/model-00104-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..294e30c29f66c665e9315e34767304b96c521df5 --- /dev/null +++ b/bf16/model-00104-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadef98b6592480b68603880edfe059fb8bac33e41397b9af31e73e045531995 +size 8602554224 diff --git a/bf16/model-00105-of-000163.safetensors b/bf16/model-00105-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..844adfb6b7dacf1731534edd9eb4ca0a4f1167fc --- /dev/null +++ b/bf16/model-00105-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62bda691b9fc6c9f9d56a2239f7083c0df317bb3469211a8e1cb6499d65c2c47 +size 8602554448 diff --git a/bf16/model-00106-of-000163.safetensors b/bf16/model-00106-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e90f50ed4c70d36ffb68d5b9980125650f5f174 --- /dev/null +++ b/bf16/model-00106-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e635c1005f4db9557d5505a060f8407b01d7d5066482c7f1a88a7be40690a2d1 +size 8597379040 diff --git a/bf16/model-00107-of-000163.safetensors b/bf16/model-00107-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3062a709ae1d248d71a11d0eb65e3d006b90f3e4 --- /dev/null +++ b/bf16/model-00107-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72a5b062dafb030b15b8a74a12ffab48bd3e12722c507c9e6d2db451c69ba250 +size 8602554320 diff --git a/bf16/model-00108-of-000163.safetensors b/bf16/model-00108-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92ee7921160b04ca642119b766ad5b5980003c07 --- /dev/null +++ b/bf16/model-00108-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cee00ac1a9c6f952d0152a252488212ee6ca0810030a1644d8a67feb1606669 +size 8602554448 diff --git a/bf16/model-00109-of-000163.safetensors b/bf16/model-00109-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f2b5691755e9f809f2fc77cacb2945229e36379a --- /dev/null +++ b/bf16/model-00109-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6f74a8f27c2415290ee5f5b759b960169d666fc4d0ef6a07cf75c67cf93c7b +size 8597378944 diff --git a/bf16/model-00110-of-000163.safetensors b/bf16/model-00110-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1316c0c583e4cff23df8ab0d104d1cb433629aa9 --- /dev/null +++ b/bf16/model-00110-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961fa794f69b955f4b3248963f3f7a25ef78cb7d5387dcb610e544b9d1eae2f0 +size 8602554416 diff --git a/bf16/model-00111-of-000163.safetensors b/bf16/model-00111-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..99d41a637dd26e74c61ec0dbda16088c9632bbf4 --- /dev/null +++ b/bf16/model-00111-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:953a747d571c14fcfbf990cc835239ce659ea5ae6e666b8b64ff5726703cb2d1 +size 8597379144 diff --git a/bf16/model-00112-of-000163.safetensors b/bf16/model-00112-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36911f00f7d9ef4004da818f6134d6f5e5d3d0df --- /dev/null +++ b/bf16/model-00112-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74dd941e80c9ed54b706af7cad08017fc2d143dbb93e55baf193e94f99151933 +size 8602554216 diff --git a/bf16/model-00113-of-000163.safetensors b/bf16/model-00113-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b4b1fb04f391991d7338321418422e8d03847cf --- /dev/null +++ b/bf16/model-00113-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328b812d19514aab1b4f69961b939ab8d4b7419b66374cb5e591ae54900d5499 +size 8602554448 diff --git a/bf16/model-00114-of-000163.safetensors b/bf16/model-00114-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..115fa20ba028a8b0c92ee2aeeb86dfbb21cba82d --- /dev/null +++ b/bf16/model-00114-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01cd06617674e8e8c63b5b7082482a6ca3b48ffb1032cfc398746e6431ae9889 +size 8597379056 diff --git a/bf16/model-00115-of-000163.safetensors b/bf16/model-00115-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56067ff302f8e2092cc8631e09ac36479f57102d --- /dev/null +++ b/bf16/model-00115-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99677efdc674ab74d295b725d478c153fdc84ecdea0f41b713d0a0229f3ec6c +size 8602554312 diff --git a/bf16/model-00116-of-000163.safetensors b/bf16/model-00116-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55ed002f7821597432aa390686d4a504edef7b6d --- /dev/null +++ b/bf16/model-00116-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b736ef3b71b5699a4a23701d6ab1cf49231ce972b55864cb1f51301c876bfb +size 8602554448 diff --git a/bf16/model-00117-of-000163.safetensors b/bf16/model-00117-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..52d9e94665d9190bbed98bec09e5aa99e14b48d6 --- /dev/null +++ b/bf16/model-00117-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60011b94e3722b7de73f19749790e102f9fded2050aa8c5d3bb611ee803466bd +size 8597378960 diff --git a/bf16/model-00118-of-000163.safetensors b/bf16/model-00118-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e001f7625fd29ab841a9ac8999f8e1407a68b50 --- /dev/null +++ b/bf16/model-00118-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6700eec03362e56d1729eee325f93e83e2f9903a13c744bb80be172ee1cbc2e0 +size 8602554408 diff --git a/bf16/model-00119-of-000163.safetensors b/bf16/model-00119-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..860641e5a2df8603ea550ed16a46c909b20b14c6 --- /dev/null +++ b/bf16/model-00119-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d24b43032e50ad78e38465298d4bdae841afa4a97dc2963d63e02ce7d85673f5 +size 8597379160 diff --git a/bf16/model-00120-of-000163.safetensors b/bf16/model-00120-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da47bb27b5a6001bf3ddaa1f16b6afa877bb7472 --- /dev/null +++ b/bf16/model-00120-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1739ee190da480666fe156e39304e0d5aed90c3293e4f7f4a2fa28e5889946 +size 8602554200 diff --git a/bf16/model-00121-of-000163.safetensors b/bf16/model-00121-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3fda8f0291f4ba5da80611eb534afa5f1e91bd1e --- /dev/null +++ b/bf16/model-00121-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28ee19082633f5cd088a18a4815a9c6f64ab34ca8b776958272b6471bf621460 +size 8602554448 diff --git a/bf16/model-00122-of-000163.safetensors b/bf16/model-00122-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bffddd025b921cabfeed7b546b965114d52824c9 --- /dev/null +++ b/bf16/model-00122-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e32dd7bb05a9ee84b9ba177d43ca90aa68448953824c3cb7029f412a6366ce4 +size 3728809784 diff --git a/bf16/model-00123-of-000163.safetensors b/bf16/model-00123-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04cdff82adfc8c77cb73dfed34bad5355de57be3 --- /dev/null +++ b/bf16/model-00123-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c201933730c9ee2853b9ca88054b8fbe2c08bb3cffc00b6561d937c9140da7d6 +size 8597321376 diff --git a/bf16/model-00124-of-000163.safetensors b/bf16/model-00124-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f15a4d4627c3e26ad522371977d158fb8b1535a4 --- /dev/null +++ b/bf16/model-00124-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a905438caa30c7ae52567dced696623b6d74302e5097fb8813518975b16615b8 +size 8602554424 diff --git a/bf16/model-00125-of-000163.safetensors b/bf16/model-00125-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45b8bc3eaa7925143a4571e8e82f5f171b6b4364 --- /dev/null +++ b/bf16/model-00125-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8c1ed3245c219f0bdf5d77ab96dc269d86e3cd7cd54a376642be6e24b3f1cc0 +size 8597379136 diff --git a/bf16/model-00126-of-000163.safetensors b/bf16/model-00126-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1af15657e2b3b862aecfae09d333aa935a0d0e57 --- /dev/null +++ b/bf16/model-00126-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37b3840f05846b23494f2c63427590cde60848e425765018d962416b79e9079 +size 8602554224 diff --git a/bf16/model-00127-of-000163.safetensors b/bf16/model-00127-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fad659b163b59ad50d9ef35b335b8b0a26fd122b --- /dev/null +++ b/bf16/model-00127-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc654e03f13ab8d88632b70f64c34c89762a93fe687efa691ff2227572736449 +size 8602554448 diff --git a/bf16/model-00128-of-000163.safetensors b/bf16/model-00128-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c86e9920a54ae89491f02a42d11807691088fea --- /dev/null +++ b/bf16/model-00128-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8add7e1a58643a9d00486aceb767e6b71c2560179e2b7b5bf18802f055e59a +size 8597379040 diff --git a/bf16/model-00129-of-000163.safetensors b/bf16/model-00129-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..797f3e626647dfb8a1fc50e772f461cf708937d2 --- /dev/null +++ b/bf16/model-00129-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b66ad9ecd7173a762b21e0a042e43f4a3b07b1a9ffda9ecd03d6925663487e58 +size 8602554320 diff --git a/bf16/model-00130-of-000163.safetensors b/bf16/model-00130-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0bda0761cd80b9a49661f1888b45ab0c10ec66d8 --- /dev/null +++ b/bf16/model-00130-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eba484f52e112d6b4d37305188445047c38b03a321c61ee655b4b8c731a243b +size 8602554448 diff --git a/bf16/model-00131-of-000163.safetensors b/bf16/model-00131-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d67acca4a70278242be58f9b5cb511d35423a460 --- /dev/null +++ b/bf16/model-00131-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d399da72e1c56cc2cee52d950f308a748f290a0bb5134e31cf0f63f28f80cad5 +size 8597378944 diff --git a/bf16/model-00132-of-000163.safetensors b/bf16/model-00132-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e4c5475e62df25924784d1f8e2ff6ab0e861d9e --- /dev/null +++ b/bf16/model-00132-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa86408b2a47c4bd83ef0033b6cb193b7c22c7e3e72c94ac81d5f6d70f73fb3 +size 8602554416 diff --git a/bf16/model-00133-of-000163.safetensors b/bf16/model-00133-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6069d1b3f03d6df44be53776d7052e41082c6ca --- /dev/null +++ b/bf16/model-00133-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b6721eb72a7504029c1727f239f32567c038b034f4f4e76618039d7f14646e +size 8597379144 diff --git a/bf16/model-00134-of-000163.safetensors b/bf16/model-00134-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d1d0ef8501dabb6f858ed33f3bfe135d9d2c31f --- /dev/null +++ b/bf16/model-00134-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b602d03b05507621f80e785960c738e569a30e6f1efa18008c7e56b9004f237 +size 8602554216 diff --git a/bf16/model-00135-of-000163.safetensors b/bf16/model-00135-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07def3c778bde6529d75b542d1bc37ffb9d3f82c --- /dev/null +++ b/bf16/model-00135-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e90cda23a46e5789947053dc52c80eb9e190ce98decdc81532c151671226364 +size 8602554448 diff --git a/bf16/model-00136-of-000163.safetensors b/bf16/model-00136-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9b17699471fb883c12d619e59009f8ea9a827936 --- /dev/null +++ b/bf16/model-00136-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d4eba06054ac7f2f62db86f2a0ba5ca85621b09ece697f31331090eb646876 +size 8597379056 diff --git a/bf16/model-00137-of-000163.safetensors b/bf16/model-00137-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..51fde9346201b3e278dd24b70e0c54bdbf7af1a8 --- /dev/null +++ b/bf16/model-00137-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec2560e9ca39e8d24ee7ea0ffaadd3ef368018d97de563eb1f5b95931884ebb +size 8602554312 diff --git a/bf16/model-00138-of-000163.safetensors b/bf16/model-00138-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..962820cb37cbccd93e265a76b19285e89a104105 --- /dev/null +++ b/bf16/model-00138-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba35620340b979b4c77c03502d1005297a43262b070124bc99e57d3030f1a90f +size 8602554448 diff --git a/bf16/model-00139-of-000163.safetensors b/bf16/model-00139-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..196781de83210bac839f91ab33421a6334395416 --- /dev/null +++ b/bf16/model-00139-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4352764da21d77dc71cc00f0f130cfbeb1cfb6706af8f52eb826e09d1f4bc918 +size 8597378960 diff --git a/bf16/model-00140-of-000163.safetensors b/bf16/model-00140-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..091d5c1c2ff9bed322ab92f49cb57b8c6125f778 --- /dev/null +++ b/bf16/model-00140-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61dcc60640acbaefbe07c3affb6b578eda97fb354e0e05582f2bce26af3487a +size 8602554408 diff --git a/bf16/model-00141-of-000163.safetensors b/bf16/model-00141-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1814ad29ca0f0403a3035029bcbd74f63b872780 --- /dev/null +++ b/bf16/model-00141-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9030a73736b73d68493df185ac13e405a383cea03a94792bda8345ce05b09a8f +size 6488673688 diff --git a/bf16/model-00142-of-000163.safetensors b/bf16/model-00142-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08cfecbfc2a271e5d6882516c7b1e102b0f620b3 --- /dev/null +++ b/bf16/model-00142-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cb262735677aa404ffce5d05b5320bec03aad87e579308ce06b1570c365226 +size 8597321376 diff --git a/bf16/model-00143-of-000163.safetensors b/bf16/model-00143-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c1aa63e8e1768a54b94f2b963a03c72f889f16ea --- /dev/null +++ b/bf16/model-00143-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc5ea3ac5653ec5ffbfc904787c6b729d6c6798643c07b550e753eda308bee0c +size 8602554424 diff --git a/bf16/model-00144-of-000163.safetensors b/bf16/model-00144-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2d66ccbb02f809f7823bad084e355a8fc19cfea0 --- /dev/null +++ b/bf16/model-00144-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c4e5057164cf75a2bf4ec1f6626f83d7120d1e0c22d6042f660e26756e554a +size 8597379136 diff --git a/bf16/model-00145-of-000163.safetensors b/bf16/model-00145-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..122b86a11f3b9aa95bc107dbf195cd0016ba3795 --- /dev/null +++ b/bf16/model-00145-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8e2dabf74fc860a4c834708ff78624c151dfb313dbbcd6bf79e536d5d5715c +size 8602554224 diff --git a/bf16/model-00146-of-000163.safetensors b/bf16/model-00146-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58713b1d1dfba414ab7677acc8bf9e4ab8c93a35 --- /dev/null +++ b/bf16/model-00146-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f77ae9ce333ca06f400729b8497571ffa994d42b1ed2015d218fd4d8dff2815 +size 8602554448 diff --git a/bf16/model-00147-of-000163.safetensors b/bf16/model-00147-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ac9589f6ed0a7db76d9e1d506f192754c2b11db --- /dev/null +++ b/bf16/model-00147-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e7242b79736c59790d57e32144228a3d3b204424c63cf4332bb61dbd04c90fd +size 8597379040 diff --git a/bf16/model-00148-of-000163.safetensors b/bf16/model-00148-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..029436c81bf8341acf4dd4aaae84de28dd1b3479 --- /dev/null +++ b/bf16/model-00148-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b20166b0e412cc5d6e8d57ed8cf57549c3687c723eee9ad7915fcb0a19581711 +size 8602554320 diff --git a/bf16/model-00149-of-000163.safetensors b/bf16/model-00149-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..671f05c232423868ad7d9317e758b7c1548c57c5 --- /dev/null +++ b/bf16/model-00149-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853a8851eea04f50f983131655f7b2dfdcc42a1a9d98604d3c0a7fec19aef466 +size 8602554448 diff --git a/bf16/model-00150-of-000163.safetensors b/bf16/model-00150-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..961c679125dd65fc8285d760ae7828f4eca09e66 --- /dev/null +++ b/bf16/model-00150-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c27a70f07822aa4b88c9a5d56a04a820120027de83a26804c09cd6150755ecf +size 8597378944 diff --git a/bf16/model-00151-of-000163.safetensors b/bf16/model-00151-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64ad571c22de8198eabe3edd452619ff048235fe --- /dev/null +++ b/bf16/model-00151-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d14eb182f24271bb26d4c5806cbf91b2829dd7177267ad287347df3b8105c8f +size 8602554416 diff --git a/bf16/model-00152-of-000163.safetensors b/bf16/model-00152-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a1b33257614a7523ead81baa6791ea5110998cf6 --- /dev/null +++ b/bf16/model-00152-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d05e576cb451aceea180c8672955f68e5a1eb3646c9a8620c839c49143d9af23 +size 8597379144 diff --git a/bf16/model-00153-of-000163.safetensors b/bf16/model-00153-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d2167d33273fe5279859ebd62d2d6f2db645b39 --- /dev/null +++ b/bf16/model-00153-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d59b8c221471318f072795c92620eb45575df3c8ca6a7520427e415a82f0330b +size 8602554216 diff --git a/bf16/model-00154-of-000163.safetensors b/bf16/model-00154-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac694d2a29755adb4f341d465be239821e64d0cc --- /dev/null +++ b/bf16/model-00154-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c79fe6fa42daf288ea948718c045d2c1df409a5e5274ae3468e91ce55933b80 +size 8602554448 diff --git a/bf16/model-00155-of-000163.safetensors b/bf16/model-00155-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..373833239cd9c3dba6d5bf11d0e46d73832a623f --- /dev/null +++ b/bf16/model-00155-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2441c4b6d37e934d7f8ea6fbdeb8f8aa12d8017f83f6d9233d1bb14005114249 +size 8597379056 diff --git a/bf16/model-00156-of-000163.safetensors b/bf16/model-00156-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..24f4b9e9a312fb1b22823aedb0a91cd0e4bcfd61 --- /dev/null +++ b/bf16/model-00156-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcba73278f66600e77c76686bb7ba7054b06abc81d100f16d8aae7269212578d +size 8602554312 diff --git a/bf16/model-00157-of-000163.safetensors b/bf16/model-00157-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a581f3eef05fd6aa576e8662fcd4e272581859a7 --- /dev/null +++ b/bf16/model-00157-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:699181d28e6511ef767242b8b8ed94e19b22b17f9a945a6c6d479b09dc902bd3 +size 8602554448 diff --git a/bf16/model-00158-of-000163.safetensors b/bf16/model-00158-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c579f0156077b255d47f4eabef6bd7eeb344e096 --- /dev/null +++ b/bf16/model-00158-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77de9037f3a620fa765887c0663479466713191133c3a6dc7ec0ec5ac58c4193 +size 8597378960 diff --git a/bf16/model-00159-of-000163.safetensors b/bf16/model-00159-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50ed645f14cc4e47c3b66993bf43ee614831b5a8 --- /dev/null +++ b/bf16/model-00159-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049f95e9a95e90d66440e7262810937bb7a39eedca19313df37b2bd41ac349e9 +size 8602554408 diff --git a/bf16/model-00160-of-000163.safetensors b/bf16/model-00160-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2cbb933dd7ab5ccd74367a83f379a1eaf4c79c01 --- /dev/null +++ b/bf16/model-00160-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba8c130a3abc9c88fceca04ca2b50b05fe44bffefe82607d9f0277b0d6b8978 +size 8716280272 diff --git a/bf16/model-00161-of-000163.safetensors b/bf16/model-00161-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8358cff188f18a4b6385820820d8fb0438f94fc8 --- /dev/null +++ b/bf16/model-00161-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247ab850b6b3a64517dd2b54da3bcfcc1ddb2cd7563ca70e58d82cf5af92ba3f +size 8604785088 diff --git a/bf16/model-00162-of-000163.safetensors b/bf16/model-00162-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9955be2f7a0038010df656809e4eac52ee76db3b --- /dev/null +++ b/bf16/model-00162-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:174a870a3d2f84de95889a639022f667f132c89dc499f5b1bfd36bf0edcea778 +size 8602554440 diff --git a/bf16/model-00163-of-000163.safetensors b/bf16/model-00163-of-000163.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..361d1d284fea9b62fa98bfade1dd9f80561ba60d --- /dev/null +++ b/bf16/model-00163-of-000163.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73137f3dfd4c4a056fe16e921a7195c1b87960e22d7b868f2db4554f311fd1df +size 9373388568 diff --git a/bf16/model.safetensors.index.json b/bf16/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..d65d5b5daaf7ecc971198f3533c072ff0da42238 --- /dev/null +++ b/bf16/model.safetensors.index.json @@ -0,0 +1,46498 @@ +{ + "metadata": {}, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.indexer.wq_b.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.indexer.wk.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.indexer.k_norm.weight": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.indexer.k_norm.bias": "model-00001-of-000163.safetensors", + "model.layers.0.self_attn.indexer.weights_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.q_a_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.q_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.indexer.wq_b.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.indexer.wk.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.indexer.k_norm.weight": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.indexer.k_norm.bias": "model-00001-of-000163.safetensors", + "model.layers.1.self_attn.indexer.weights_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.q_a_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.q_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.indexer.wq_b.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.indexer.wk.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.indexer.k_norm.weight": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.indexer.k_norm.bias": "model-00001-of-000163.safetensors", + "model.layers.2.self_attn.indexer.weights_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.q_a_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.q_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.q_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.indexer.wq_b.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.indexer.wk.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.indexer.k_norm.weight": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.indexer.k_norm.bias": "model-00001-of-000163.safetensors", + "model.layers.3.self_attn.indexer.weights_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.gate.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00001-of-000163.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00002-of-000163.safetensors", + "model.layers.3.mlp.experts.128.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.128.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.128.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.129.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.129.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.129.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.130.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.130.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.130.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.131.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.131.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.131.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.132.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.132.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.132.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.133.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.133.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.133.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.134.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.134.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.134.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.135.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.135.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.135.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.136.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.136.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.136.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.137.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.137.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.137.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.138.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.138.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.138.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.139.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.139.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.139.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.140.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.140.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.140.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.141.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.141.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.141.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.142.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.142.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.142.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.143.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.143.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.143.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.144.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.144.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.144.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.145.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.145.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.145.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.146.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.146.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.146.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.147.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.147.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.147.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.148.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.148.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.148.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.149.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.149.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.149.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.150.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.150.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.150.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.151.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.151.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.151.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.152.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.152.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.152.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.153.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.153.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.153.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.154.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.154.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.154.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.155.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.155.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.155.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.156.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.156.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.156.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.157.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.157.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.157.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.158.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.158.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.158.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.159.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.159.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.159.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.160.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.160.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.160.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.161.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.161.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.161.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.162.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.162.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.162.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.163.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.163.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.163.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.164.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.164.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.164.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.165.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.165.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.165.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.166.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.166.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.166.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.167.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.167.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.167.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.168.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.168.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.168.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.169.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.169.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.169.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.170.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.170.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.170.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.171.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.171.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.171.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.172.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.172.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.172.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.173.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.173.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.173.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.174.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.174.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.174.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.175.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.175.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.175.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.176.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.176.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.176.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.177.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.177.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.177.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.178.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.178.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.178.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.179.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.179.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.179.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.180.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.180.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.180.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.181.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.181.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.181.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.182.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.182.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.182.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.183.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.183.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.183.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.184.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.184.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.184.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.185.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.185.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.185.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.186.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.186.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.186.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.187.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.187.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.187.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.188.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.188.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.188.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.189.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.189.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.189.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.190.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.190.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.190.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.191.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.191.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.191.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.192.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.192.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.192.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.193.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.193.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.193.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.194.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.194.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.194.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.195.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.195.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.195.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.196.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.196.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.196.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.197.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.197.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.197.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.198.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.198.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.198.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.199.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.199.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.199.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.200.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.200.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.200.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.201.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.201.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.201.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.202.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.202.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.202.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.203.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.203.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.203.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.204.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.204.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.204.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.205.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.205.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.205.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.206.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.206.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.206.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.207.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.207.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.207.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.208.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.208.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.208.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.209.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.209.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.209.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.210.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.210.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.210.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.211.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.211.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.211.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.212.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.212.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.212.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.213.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.213.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.213.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.214.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.214.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.214.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.215.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.215.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.215.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.216.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.216.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.216.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.217.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.217.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.217.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.218.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.218.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.218.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.219.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.219.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.219.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.220.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.220.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.220.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.221.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.221.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.221.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.222.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.222.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.222.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.223.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.223.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.223.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.224.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.224.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.224.down_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.225.gate_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.225.up_proj.weight": "model-00003-of-000163.safetensors", + "model.layers.3.mlp.experts.225.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.226.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.226.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.226.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.227.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.227.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.227.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.228.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.228.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.228.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.229.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.229.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.229.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.230.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.230.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.230.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.231.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.231.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.231.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.232.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.232.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.232.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.233.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.233.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.233.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.234.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.234.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.234.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.235.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.235.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.235.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.236.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.236.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.236.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.237.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.237.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.237.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.238.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.238.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.238.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.239.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.239.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.239.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.240.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.240.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.240.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.241.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.241.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.241.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.242.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.242.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.242.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.243.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.243.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.243.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.244.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.244.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.244.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.245.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.245.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.245.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.246.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.246.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.246.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.247.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.247.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.247.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.248.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.248.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.248.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.249.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.249.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.249.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.250.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.250.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.250.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.251.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.251.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.251.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.252.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.252.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.252.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.253.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.253.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.253.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.254.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.254.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.254.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.255.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.255.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.mlp.experts.255.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-000163.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.q_a_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.q_a_layernorm.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.q_b_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.kv_b_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.indexer.wq_b.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.indexer.wk.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.indexer.k_norm.weight": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.indexer.k_norm.bias": "model-00004-of-000163.safetensors", + "model.layers.4.self_attn.indexer.weights_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.gate.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00004-of-000163.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.128.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.128.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.128.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.129.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.129.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.129.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.130.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.130.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.130.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.131.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.131.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.131.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.132.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.132.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.132.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.133.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.133.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.133.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.134.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.134.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.134.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.135.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.135.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.135.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.136.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.136.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.136.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.137.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.137.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.137.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.138.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.138.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.138.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.139.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.139.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.139.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.140.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.140.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.140.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.141.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.141.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.141.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.142.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.142.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.142.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.143.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.143.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.143.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.144.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.144.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.144.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.145.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.145.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.145.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.146.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.146.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.146.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.147.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.147.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.147.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.148.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.148.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.148.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.149.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.149.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.149.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.150.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.150.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.150.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.151.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.151.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.151.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.152.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.152.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.152.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.153.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.153.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.153.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.154.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.154.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.154.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.155.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.155.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.155.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.156.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.156.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.156.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.157.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.157.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.157.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.158.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.158.up_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.158.down_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.159.gate_proj.weight": "model-00005-of-000163.safetensors", + "model.layers.4.mlp.experts.159.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.159.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.160.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.160.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.160.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.161.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.161.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.161.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.162.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.162.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.162.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.163.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.163.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.163.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.164.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.164.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.164.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.165.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.165.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.165.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.166.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.166.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.166.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.167.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.167.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.167.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.168.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.168.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.168.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.169.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.169.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.169.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.170.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.170.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.170.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.171.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.171.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.171.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.172.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.172.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.172.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.173.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.173.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.173.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.174.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.174.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.174.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.175.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.175.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.175.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.176.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.176.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.176.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.177.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.177.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.177.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.178.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.178.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.178.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.179.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.179.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.179.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.180.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.180.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.180.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.181.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.181.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.181.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.182.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.182.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.182.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.183.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.183.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.183.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.184.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.184.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.184.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.185.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.185.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.185.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.186.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.186.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.186.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.187.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.187.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.187.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.188.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.188.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.188.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.189.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.189.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.189.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.190.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.190.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.190.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.191.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.191.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.191.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.192.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.192.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.192.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.193.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.193.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.193.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.194.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.194.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.194.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.195.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.195.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.195.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.196.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.196.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.196.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.197.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.197.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.197.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.198.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.198.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.198.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.199.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.199.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.199.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.200.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.200.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.200.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.201.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.201.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.201.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.202.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.202.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.202.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.203.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.203.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.203.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.204.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.204.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.204.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.205.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.205.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.205.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.206.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.206.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.206.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.207.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.207.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.207.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.208.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.208.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.208.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.209.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.209.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.209.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.210.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.210.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.210.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.211.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.211.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.211.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.212.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.212.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.212.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.213.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.213.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.213.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.214.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.214.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.214.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.215.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.215.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.215.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.216.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.216.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.216.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.217.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.217.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.217.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.218.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.218.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.218.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.219.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.219.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.219.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.220.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.220.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.220.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.221.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.221.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.221.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.222.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.222.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.222.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.223.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.223.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.223.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.224.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.224.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.224.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.225.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.225.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.225.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.226.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.226.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.226.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.227.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.227.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.227.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.228.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.228.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.228.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.229.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.229.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.229.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.230.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.230.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.230.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.231.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.231.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.231.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.232.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.232.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.232.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.233.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.233.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.233.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.234.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.234.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.234.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.235.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.235.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.235.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.236.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.236.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.236.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.237.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.237.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.237.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.238.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.238.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.238.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.239.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.239.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.239.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.240.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.240.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.240.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.241.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.241.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.241.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.242.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.242.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.242.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.243.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.243.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.243.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.244.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.244.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.244.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.245.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.245.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.245.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.246.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.246.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.246.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.247.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.247.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.247.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.248.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.248.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.248.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.249.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.249.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.249.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.250.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.250.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.250.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.251.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.251.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.251.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.252.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.252.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.252.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.253.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.253.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.253.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.254.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.254.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.254.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.255.gate_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.255.up_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.mlp.experts.255.down_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.4.input_layernorm.weight": "model-00006-of-000163.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00006-of-000163.safetensors", + "model.layers.5.self_attn.q_a_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.5.self_attn.q_a_layernorm.weight": "model-00006-of-000163.safetensors", + "model.layers.5.self_attn.q_b_proj.weight": "model-00006-of-000163.safetensors", + "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.kv_b_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.indexer.wq_b.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.indexer.wk.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.indexer.k_norm.weight": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.indexer.k_norm.bias": "model-00007-of-000163.safetensors", + "model.layers.5.self_attn.indexer.weights_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.gate.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00007-of-000163.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.128.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.128.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.128.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.129.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.129.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.129.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.130.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.130.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.130.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.131.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.131.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.131.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.132.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.132.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.132.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.133.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.133.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.133.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.134.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.134.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.134.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.135.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.135.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.135.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.136.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.136.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.136.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.137.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.137.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.137.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.138.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.138.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.138.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.139.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.139.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.139.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.140.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.140.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.140.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.141.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.141.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.141.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.142.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.142.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.142.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.143.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.143.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.143.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.144.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.144.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.144.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.145.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.145.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.145.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.146.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.146.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.146.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.147.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.147.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.147.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.148.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.148.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.148.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.149.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.149.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.149.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.150.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.150.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.150.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.151.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.151.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.151.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.152.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.152.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.152.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.153.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.153.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.153.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.154.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.154.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.154.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.155.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.155.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.155.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.156.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.156.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.156.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.157.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.157.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.157.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.158.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.158.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.158.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.159.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.159.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.159.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.160.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.160.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.160.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.161.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.161.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.161.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.162.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.162.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.162.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.163.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.163.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.163.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.164.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.164.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.164.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.165.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.165.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.165.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.166.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.166.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.166.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.167.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.167.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.167.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.168.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.168.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.168.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.169.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.169.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.169.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.170.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.170.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.170.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.171.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.171.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.171.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.172.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.172.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.172.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.173.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.173.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.173.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.174.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.174.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.174.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.175.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.175.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.175.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.176.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.176.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.176.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.177.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.177.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.177.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.178.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.178.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.178.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.179.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.179.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.179.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.180.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.180.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.180.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.181.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.181.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.181.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.182.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.182.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.182.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.183.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.183.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.183.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.184.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.184.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.184.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.185.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.185.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.185.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.186.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.186.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.186.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.187.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.187.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.187.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.188.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.188.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.188.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.189.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.189.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.189.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.190.gate_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.190.up_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.190.down_proj.weight": "model-00008-of-000163.safetensors", + "model.layers.5.mlp.experts.191.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.191.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.191.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.192.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.192.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.192.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.193.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.193.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.193.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.194.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.194.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.194.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.195.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.195.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.195.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.196.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.196.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.196.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.197.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.197.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.197.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.198.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.198.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.198.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.199.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.199.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.199.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.200.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.200.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.200.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.201.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.201.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.201.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.202.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.202.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.202.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.203.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.203.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.203.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.204.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.204.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.204.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.205.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.205.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.205.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.206.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.206.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.206.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.207.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.207.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.207.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.208.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.208.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.208.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.209.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.209.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.209.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.210.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.210.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.210.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.211.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.211.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.211.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.212.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.212.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.212.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.213.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.213.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.213.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.214.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.214.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.214.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.215.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.215.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.215.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.216.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.216.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.216.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.217.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.217.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.217.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.218.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.218.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.218.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.219.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.219.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.219.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.220.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.220.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.220.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.221.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.221.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.221.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.222.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.222.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.222.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.223.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.223.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.223.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.224.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.224.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.224.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.225.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.225.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.225.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.226.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.226.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.226.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.227.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.227.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.227.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.228.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.228.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.228.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.229.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.229.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.229.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.230.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.230.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.230.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.231.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.231.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.231.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.232.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.232.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.232.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.233.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.233.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.233.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.234.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.234.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.234.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.235.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.235.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.235.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.236.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.236.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.236.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.237.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.237.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.237.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.238.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.238.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.238.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.239.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.239.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.239.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.240.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.240.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.240.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.241.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.241.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.241.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.242.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.242.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.242.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.243.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.243.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.243.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.244.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.244.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.244.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.245.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.245.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.245.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.246.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.246.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.246.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.247.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.247.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.247.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.248.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.248.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.248.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.249.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.249.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.249.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.250.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.250.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.250.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.251.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.251.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.251.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.252.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.252.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.252.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.253.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.253.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.253.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.254.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.254.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.254.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.255.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.255.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.mlp.experts.255.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.5.input_layernorm.weight": "model-00009-of-000163.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.q_a_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.q_a_layernorm.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.q_b_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.kv_b_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.indexer.wq_b.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.indexer.wk.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.indexer.k_norm.weight": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.indexer.k_norm.bias": "model-00009-of-000163.safetensors", + "model.layers.6.self_attn.indexer.weights_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.gate.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00009-of-000163.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00010-of-000163.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.128.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.128.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.128.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.129.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.129.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.129.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.130.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.130.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.130.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.131.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.131.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.131.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.132.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.132.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.132.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.133.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.133.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.133.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.134.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.134.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.134.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.135.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.135.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.135.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.136.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.136.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.136.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.137.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.137.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.137.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.138.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.138.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.138.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.139.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.139.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.139.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.140.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.140.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.140.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.141.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.141.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.141.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.142.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.142.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.142.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.143.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.143.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.143.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.144.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.144.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.144.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.145.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.145.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.145.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.146.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.146.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.146.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.147.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.147.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.147.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.148.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.148.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.148.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.149.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.149.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.149.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.150.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.150.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.150.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.151.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.151.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.151.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.152.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.152.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.152.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.153.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.153.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.153.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.154.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.154.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.154.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.155.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.155.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.155.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.156.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.156.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.156.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.157.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.157.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.157.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.158.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.158.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.158.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.159.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.159.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.159.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.160.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.160.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.160.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.161.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.161.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.161.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.162.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.162.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.162.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.163.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.163.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.163.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.164.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.164.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.164.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.165.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.165.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.165.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.166.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.166.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.166.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.167.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.167.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.167.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.168.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.168.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.168.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.169.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.169.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.169.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.170.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.170.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.170.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.171.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.171.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.171.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.172.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.172.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.172.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.173.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.173.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.173.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.174.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.174.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.174.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.175.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.175.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.175.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.176.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.176.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.176.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.177.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.177.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.177.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.178.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.178.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.178.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.179.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.179.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.179.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.180.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.180.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.180.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.181.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.181.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.181.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.182.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.182.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.182.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.183.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.183.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.183.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.184.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.184.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.184.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.185.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.185.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.185.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.186.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.186.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.186.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.187.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.187.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.187.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.188.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.188.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.188.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.189.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.189.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.189.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.190.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.190.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.190.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.191.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.191.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.191.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.192.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.192.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.192.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.193.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.193.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.193.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.194.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.194.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.194.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.195.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.195.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.195.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.196.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.196.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.196.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.197.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.197.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.197.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.198.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.198.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.198.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.199.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.199.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.199.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.200.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.200.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.200.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.201.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.201.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.201.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.202.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.202.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.202.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.203.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.203.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.203.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.204.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.204.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.204.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.205.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.205.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.205.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.206.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.206.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.206.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.207.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.207.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.207.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.208.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.208.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.208.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.209.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.209.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.209.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.210.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.210.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.210.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.211.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.211.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.211.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.212.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.212.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.212.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.213.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.213.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.213.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.214.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.214.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.214.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.215.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.215.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.215.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.216.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.216.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.216.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.217.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.217.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.217.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.218.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.218.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.218.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.219.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.219.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.219.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.220.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.220.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.220.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.221.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.221.up_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.221.down_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.222.gate_proj.weight": "model-00011-of-000163.safetensors", + "model.layers.6.mlp.experts.222.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.222.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.223.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.223.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.223.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.224.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.224.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.224.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.225.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.225.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.225.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.226.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.226.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.226.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.227.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.227.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.227.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.228.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.228.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.228.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.229.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.229.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.229.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.230.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.230.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.230.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.231.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.231.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.231.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.232.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.232.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.232.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.233.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.233.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.233.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.234.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.234.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.234.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.235.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.235.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.235.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.236.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.236.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.236.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.237.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.237.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.237.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.238.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.238.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.238.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.239.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.239.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.239.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.240.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.240.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.240.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.241.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.241.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.241.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.242.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.242.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.242.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.243.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.243.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.243.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.244.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.244.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.244.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.245.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.245.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.245.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.246.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.246.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.246.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.247.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.247.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.247.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.248.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.248.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.248.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.249.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.249.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.249.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.250.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.250.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.250.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.251.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.251.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.251.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.252.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.252.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.252.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.253.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.253.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.253.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.254.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.254.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.254.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.255.gate_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.255.up_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.mlp.experts.255.down_proj.weight": "model-00012-of-000163.safetensors", + "model.layers.6.input_layernorm.weight": "model-00012-of-000163.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00012-of-000163.safetensors", + "model.layers.7.self_attn.q_a_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.q_a_layernorm.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.q_b_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.kv_b_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.indexer.wq_b.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.indexer.wk.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.indexer.k_norm.weight": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.indexer.k_norm.bias": "model-00013-of-000163.safetensors", + "model.layers.7.self_attn.indexer.weights_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.gate.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00013-of-000163.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.128.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.128.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.128.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.129.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.129.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.129.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.130.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.130.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.130.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.131.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.131.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.131.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.132.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.132.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.132.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.133.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.133.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.133.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.134.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.134.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.134.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.135.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.135.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.135.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.136.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.136.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.136.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.137.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.137.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.137.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.138.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.138.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.138.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.139.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.139.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.139.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.140.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.140.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.140.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.141.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.141.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.141.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.142.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.142.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.142.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.143.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.143.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.143.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.144.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.144.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.144.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.145.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.145.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.145.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.146.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.146.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.146.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.147.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.147.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.147.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.148.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.148.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.148.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.149.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.149.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.149.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.150.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.150.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.150.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.151.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.151.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.151.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.152.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.152.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.152.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.153.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.153.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.153.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.154.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.154.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.154.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.155.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.155.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.155.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.156.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.156.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.156.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.157.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.157.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.157.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.158.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.158.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.158.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.159.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.159.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.159.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.160.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.160.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.160.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.161.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.161.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.161.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.162.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.162.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.162.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.163.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.163.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.163.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.164.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.164.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.164.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.165.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.165.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.165.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.166.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.166.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.166.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.167.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.167.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.167.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.168.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.168.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.168.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.169.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.169.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.169.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.170.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.170.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.170.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.171.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.171.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.171.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.172.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.172.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.172.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.173.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.173.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.173.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.174.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.174.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.174.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.175.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.175.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.175.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.176.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.176.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.176.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.177.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.177.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.177.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.178.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.178.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.178.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.179.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.179.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.179.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.180.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.180.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.180.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.181.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.181.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.181.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.182.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.182.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.182.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.183.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.183.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.183.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.184.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.184.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.184.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.185.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.185.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.185.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.186.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.186.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.186.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.187.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.187.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.187.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.188.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.188.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.188.down_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.189.gate_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.189.up_proj.weight": "model-00014-of-000163.safetensors", + "model.layers.7.mlp.experts.189.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.190.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.190.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.190.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.191.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.191.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.191.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.192.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.192.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.192.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.193.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.193.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.193.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.194.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.194.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.194.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.195.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.195.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.195.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.196.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.196.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.196.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.197.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.197.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.197.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.198.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.198.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.198.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.199.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.199.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.199.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.200.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.200.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.200.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.201.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.201.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.201.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.202.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.202.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.202.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.203.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.203.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.203.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.204.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.204.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.204.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.205.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.205.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.205.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.206.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.206.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.206.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.207.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.207.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.207.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.208.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.208.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.208.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.209.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.209.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.209.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.210.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.210.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.210.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.211.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.211.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.211.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.212.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.212.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.212.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.213.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.213.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.213.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.214.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.214.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.214.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.215.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.215.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.215.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.216.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.216.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.216.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.217.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.217.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.217.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.218.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.218.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.218.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.219.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.219.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.219.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.220.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.220.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.220.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.221.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.221.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.221.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.222.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.222.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.222.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.223.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.223.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.223.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.224.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.224.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.224.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.225.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.225.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.225.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.226.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.226.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.226.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.227.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.227.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.227.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.228.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.228.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.228.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.229.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.229.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.229.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.230.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.230.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.230.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.231.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.231.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.231.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.232.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.232.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.232.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.233.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.233.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.233.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.234.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.234.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.234.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.235.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.235.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.235.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.236.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.236.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.236.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.237.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.237.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.237.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.238.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.238.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.238.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.239.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.239.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.239.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.240.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.240.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.240.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.241.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.241.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.241.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.242.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.242.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.242.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.243.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.243.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.243.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.244.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.244.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.244.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.245.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.245.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.245.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.246.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.246.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.246.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.247.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.247.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.247.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.248.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.248.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.248.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.249.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.249.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.249.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.250.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.250.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.250.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.251.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.251.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.251.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.252.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.252.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.252.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.253.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.253.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.253.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.254.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.254.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.254.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.255.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.255.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.mlp.experts.255.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.7.input_layernorm.weight": "model-00015-of-000163.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.q_a_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.q_a_layernorm.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.q_b_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.kv_b_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.indexer.wq_b.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.indexer.wk.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.indexer.k_norm.weight": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.indexer.k_norm.bias": "model-00015-of-000163.safetensors", + "model.layers.8.self_attn.indexer.weights_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.gate.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00015-of-000163.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00016-of-000163.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.128.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.128.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.128.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.129.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.129.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.129.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.130.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.130.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.130.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.131.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.131.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.131.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.132.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.132.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.132.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.133.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.133.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.133.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.134.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.134.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.134.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.135.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.135.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.135.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.136.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.136.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.136.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.137.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.137.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.137.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.138.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.138.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.138.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.139.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.139.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.139.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.140.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.140.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.140.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.141.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.141.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.141.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.142.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.142.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.142.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.143.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.143.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.143.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.144.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.144.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.144.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.145.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.145.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.145.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.146.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.146.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.146.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.147.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.147.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.147.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.148.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.148.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.148.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.149.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.149.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.149.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.150.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.150.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.150.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.151.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.151.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.151.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.152.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.152.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.152.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.153.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.153.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.153.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.154.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.154.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.154.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.155.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.155.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.155.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.156.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.156.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.156.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.157.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.157.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.157.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.158.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.158.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.158.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.159.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.159.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.159.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.160.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.160.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.160.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.161.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.161.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.161.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.162.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.162.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.162.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.163.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.163.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.163.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.164.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.164.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.164.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.165.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.165.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.165.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.166.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.166.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.166.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.167.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.167.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.167.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.168.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.168.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.168.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.169.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.169.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.169.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.170.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.170.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.170.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.171.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.171.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.171.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.172.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.172.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.172.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.173.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.173.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.173.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.174.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.174.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.174.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.175.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.175.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.175.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.176.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.176.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.176.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.177.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.177.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.177.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.178.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.178.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.178.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.179.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.179.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.179.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.180.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.180.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.180.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.181.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.181.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.181.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.182.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.182.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.182.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.183.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.183.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.183.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.184.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.184.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.184.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.185.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.185.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.185.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.186.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.186.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.186.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.187.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.187.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.187.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.188.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.188.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.188.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.189.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.189.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.189.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.190.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.190.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.190.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.191.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.191.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.191.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.192.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.192.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.192.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.193.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.193.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.193.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.194.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.194.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.194.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.195.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.195.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.195.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.196.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.196.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.196.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.197.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.197.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.197.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.198.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.198.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.198.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.199.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.199.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.199.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.200.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.200.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.200.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.201.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.201.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.201.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.202.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.202.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.202.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.203.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.203.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.203.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.204.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.204.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.204.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.205.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.205.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.205.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.206.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.206.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.206.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.207.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.207.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.207.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.208.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.208.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.208.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.209.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.209.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.209.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.210.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.210.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.210.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.211.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.211.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.211.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.212.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.212.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.212.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.213.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.213.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.213.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.214.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.214.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.214.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.215.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.215.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.215.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.216.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.216.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.216.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.217.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.217.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.217.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.218.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.218.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.218.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.219.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.219.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.219.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.220.gate_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.220.up_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.220.down_proj.weight": "model-00017-of-000163.safetensors", + "model.layers.8.mlp.experts.221.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.221.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.221.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.222.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.222.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.222.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.223.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.223.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.223.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.224.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.224.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.224.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.225.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.225.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.225.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.226.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.226.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.226.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.227.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.227.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.227.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.228.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.228.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.228.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.229.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.229.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.229.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.230.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.230.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.230.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.231.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.231.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.231.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.232.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.232.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.232.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.233.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.233.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.233.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.234.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.234.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.234.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.235.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.235.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.235.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.236.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.236.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.236.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.237.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.237.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.237.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.238.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.238.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.238.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.239.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.239.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.239.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.240.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.240.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.240.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.241.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.241.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.241.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.242.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.242.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.242.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.243.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.243.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.243.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.244.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.244.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.244.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.245.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.245.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.245.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.246.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.246.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.246.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.247.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.247.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.247.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.248.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.248.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.248.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.249.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.249.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.249.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.250.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.250.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.250.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.251.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.251.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.251.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.252.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.252.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.252.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.253.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.253.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.253.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.254.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.254.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.254.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.255.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.255.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.mlp.experts.255.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.8.input_layernorm.weight": "model-00018-of-000163.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.q_a_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.q_a_layernorm.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.q_b_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.kv_b_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.indexer.wq_b.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.indexer.wk.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.indexer.k_norm.weight": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.indexer.k_norm.bias": "model-00018-of-000163.safetensors", + "model.layers.9.self_attn.indexer.weights_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.gate.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00018-of-000163.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.128.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.128.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.128.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.129.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.129.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.129.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.130.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.130.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.130.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.131.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.131.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.131.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.132.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.132.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.132.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.133.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.133.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.133.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.134.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.134.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.134.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.135.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.135.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.135.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.136.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.136.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.136.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.137.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.137.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.137.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.138.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.138.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.138.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.139.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.139.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.139.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.140.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.140.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.140.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.141.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.141.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.141.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.142.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.142.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.142.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.143.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.143.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.143.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.144.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.144.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.144.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.145.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.145.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.145.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.146.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.146.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.146.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.147.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.147.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.147.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.148.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.148.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.148.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.149.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.149.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.149.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.150.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.150.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.150.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.151.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.151.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.151.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.152.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.152.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.152.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.153.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.153.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.153.down_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.154.gate_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.154.up_proj.weight": "model-00019-of-000163.safetensors", + "model.layers.9.mlp.experts.154.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.155.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.155.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.155.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.156.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.156.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.156.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.157.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.157.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.157.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.158.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.158.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.158.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.159.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.159.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.159.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.160.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.160.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.160.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.161.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.161.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.161.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.162.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.162.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.162.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.163.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.163.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.163.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.164.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.164.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.164.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.165.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.165.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.165.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.166.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.166.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.166.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.167.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.167.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.167.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.168.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.168.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.168.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.169.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.169.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.169.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.170.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.170.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.170.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.171.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.171.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.171.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.172.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.172.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.172.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.173.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.173.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.173.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.174.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.174.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.174.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.175.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.175.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.175.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.176.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.176.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.176.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.177.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.177.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.177.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.178.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.178.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.178.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.179.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.179.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.179.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.180.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.180.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.180.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.181.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.181.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.181.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.182.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.182.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.182.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.183.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.183.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.183.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.184.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.184.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.184.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.185.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.185.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.185.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.186.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.186.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.186.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.187.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.187.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.187.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.188.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.188.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.188.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.189.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.189.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.189.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.190.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.190.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.190.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.191.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.191.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.191.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.192.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.192.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.192.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.193.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.193.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.193.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.194.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.194.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.194.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.195.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.195.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.195.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.196.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.196.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.196.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.197.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.197.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.197.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.198.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.198.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.198.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.199.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.199.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.199.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.200.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.200.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.200.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.201.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.201.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.201.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.202.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.202.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.202.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.203.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.203.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.203.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.204.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.204.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.204.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.205.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.205.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.205.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.206.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.206.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.206.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.207.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.207.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.207.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.208.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.208.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.208.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.209.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.209.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.209.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.210.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.210.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.210.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.211.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.211.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.211.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.212.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.212.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.212.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.213.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.213.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.213.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.214.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.214.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.214.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.215.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.215.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.215.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.216.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.216.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.216.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.217.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.217.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.217.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.218.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.218.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.218.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.219.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.219.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.219.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.220.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.220.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.220.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.221.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.221.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.221.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.222.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.222.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.222.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.223.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.223.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.223.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.224.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.224.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.224.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.225.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.225.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.225.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.226.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.226.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.226.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.227.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.227.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.227.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.228.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.228.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.228.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.229.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.229.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.229.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.230.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.230.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.230.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.231.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.231.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.231.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.232.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.232.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.232.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.233.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.233.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.233.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.234.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.234.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.234.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.235.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.235.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.235.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.236.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.236.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.236.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.237.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.237.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.237.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.238.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.238.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.238.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.239.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.239.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.239.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.240.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.240.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.240.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.241.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.241.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.241.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.242.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.242.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.242.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.243.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.243.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.243.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.244.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.244.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.244.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.245.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.245.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.245.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.246.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.246.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.246.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.247.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.247.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.247.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.248.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.248.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.248.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.249.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.249.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.249.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.250.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.250.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.250.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.251.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.251.up_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.251.down_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.252.gate_proj.weight": "model-00020-of-000163.safetensors", + "model.layers.9.mlp.experts.252.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.252.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.253.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.253.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.253.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.254.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.254.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.254.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.255.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.255.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.mlp.experts.255.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.9.input_layernorm.weight": "model-00021-of-000163.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.q_a_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.q_a_layernorm.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.q_b_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.kv_b_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.indexer.wq_b.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.indexer.wk.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.indexer.k_norm.weight": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.indexer.k_norm.bias": "model-00021-of-000163.safetensors", + "model.layers.10.self_attn.indexer.weights_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.gate.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00021-of-000163.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.128.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.128.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.128.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.129.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.129.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.129.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.130.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.130.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.130.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.131.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.131.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.131.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.132.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.132.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.132.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.133.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.133.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.133.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.134.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.134.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.134.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.135.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.135.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.135.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.136.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.136.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.136.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.137.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.137.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.137.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.138.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.138.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.138.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.139.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.139.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.139.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.140.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.140.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.140.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.141.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.141.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.141.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.142.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.142.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.142.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.143.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.143.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.143.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.144.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.144.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.144.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.145.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.145.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.145.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.146.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.146.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.146.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.147.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.147.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.147.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.148.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.148.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.148.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.149.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.149.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.149.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.150.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.150.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.150.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.151.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.151.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.151.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.152.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.152.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.152.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.153.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.153.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.153.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.154.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.154.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.154.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.155.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.155.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.155.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.156.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.156.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.156.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.157.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.157.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.157.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.158.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.158.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.158.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.159.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.159.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.159.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.160.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.160.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.160.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.161.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.161.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.161.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.162.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.162.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.162.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.163.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.163.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.163.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.164.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.164.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.164.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.165.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.165.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.165.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.166.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.166.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.166.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.167.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.167.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.167.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.168.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.168.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.168.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.169.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.169.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.169.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.170.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.170.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.170.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.171.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.171.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.171.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.172.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.172.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.172.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.173.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.173.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.173.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.174.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.174.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.174.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.175.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.175.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.175.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.176.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.176.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.176.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.177.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.177.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.177.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.178.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.178.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.178.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.179.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.179.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.179.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.180.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.180.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.180.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.181.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.181.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.181.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.182.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.182.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.182.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.183.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.183.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.183.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.184.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.184.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.184.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.185.gate_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.185.up_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.185.down_proj.weight": "model-00022-of-000163.safetensors", + "model.layers.10.mlp.experts.186.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.186.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.186.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.187.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.187.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.187.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.188.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.188.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.188.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.189.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.189.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.189.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.190.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.190.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.190.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.191.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.191.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.191.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.192.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.192.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.192.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.193.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.193.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.193.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.194.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.194.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.194.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.195.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.195.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.195.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.196.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.196.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.196.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.197.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.197.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.197.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.198.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.198.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.198.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.199.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.199.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.199.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.200.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.200.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.200.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.201.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.201.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.201.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.202.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.202.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.202.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.203.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.203.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.203.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.204.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.204.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.204.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.205.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.205.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.205.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.206.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.206.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.206.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.207.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.207.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.207.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.208.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.208.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.208.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.209.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.209.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.209.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.210.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.210.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.210.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.211.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.211.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.211.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.212.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.212.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.212.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.213.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.213.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.213.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.214.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.214.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.214.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.215.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.215.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.215.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.216.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.216.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.216.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.217.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.217.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.217.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.218.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.218.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.218.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.219.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.219.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.219.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.220.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.220.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.220.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.221.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.221.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.221.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.222.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.222.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.222.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.223.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.223.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.223.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.224.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.224.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.224.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.225.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.225.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.225.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.226.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.226.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.226.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.227.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.227.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.227.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.228.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.228.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.228.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.229.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.229.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.229.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.230.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.230.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.230.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.231.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.231.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.231.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.232.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.232.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.232.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.233.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.233.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.233.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.234.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.234.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.234.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.235.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.235.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.235.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.236.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.236.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.236.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.237.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.237.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.237.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.238.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.238.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.238.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.239.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.239.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.239.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.240.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.240.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.240.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.241.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.241.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.241.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.242.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.242.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.242.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.243.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.243.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.243.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.244.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.244.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.244.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.245.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.245.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.245.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.246.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.246.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.246.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.247.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.247.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.247.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.248.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.248.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.248.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.249.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.249.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.249.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.250.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.250.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.250.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.251.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.251.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.251.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.252.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.252.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.252.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.253.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.253.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.253.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.254.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.254.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.254.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.255.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.255.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.mlp.experts.255.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.10.input_layernorm.weight": "model-00023-of-000163.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.q_a_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.q_a_layernorm.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.q_b_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.kv_b_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.indexer.wq_b.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.indexer.wk.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.indexer.k_norm.weight": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.indexer.k_norm.bias": "model-00023-of-000163.safetensors", + "model.layers.11.self_attn.indexer.weights_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.gate.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00023-of-000163.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00024-of-000163.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.128.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.128.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.128.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.129.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.129.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.129.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.130.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.130.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.130.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.131.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.131.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.131.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.132.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.132.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.132.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.133.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.133.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.133.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.134.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.134.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.134.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.135.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.135.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.135.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.136.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.136.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.136.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.137.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.137.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.137.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.138.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.138.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.138.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.139.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.139.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.139.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.140.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.140.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.140.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.141.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.141.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.141.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.142.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.142.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.142.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.143.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.143.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.143.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.144.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.144.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.144.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.145.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.145.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.145.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.146.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.146.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.146.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.147.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.147.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.147.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.148.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.148.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.148.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.149.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.149.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.149.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.150.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.150.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.150.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.151.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.151.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.151.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.152.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.152.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.152.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.153.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.153.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.153.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.154.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.154.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.154.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.155.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.155.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.155.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.156.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.156.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.156.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.157.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.157.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.157.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.158.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.158.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.158.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.159.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.159.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.159.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.160.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.160.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.160.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.161.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.161.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.161.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.162.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.162.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.162.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.163.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.163.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.163.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.164.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.164.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.164.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.165.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.165.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.165.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.166.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.166.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.166.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.167.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.167.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.167.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.168.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.168.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.168.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.169.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.169.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.169.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.170.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.170.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.170.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.171.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.171.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.171.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.172.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.172.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.172.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.173.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.173.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.173.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.174.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.174.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.174.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.175.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.175.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.175.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.176.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.176.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.176.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.177.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.177.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.177.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.178.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.178.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.178.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.179.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.179.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.179.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.180.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.180.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.180.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.181.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.181.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.181.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.182.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.182.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.182.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.183.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.183.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.183.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.184.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.184.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.184.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.185.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.185.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.185.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.186.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.186.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.186.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.187.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.187.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.187.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.188.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.188.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.188.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.189.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.189.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.189.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.190.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.190.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.190.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.191.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.191.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.191.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.192.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.192.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.192.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.193.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.193.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.193.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.194.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.194.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.194.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.195.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.195.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.195.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.196.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.196.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.196.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.197.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.197.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.197.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.198.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.198.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.198.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.199.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.199.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.199.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.200.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.200.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.200.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.201.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.201.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.201.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.202.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.202.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.202.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.203.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.203.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.203.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.204.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.204.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.204.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.205.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.205.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.205.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.206.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.206.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.206.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.207.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.207.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.207.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.208.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.208.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.208.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.209.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.209.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.209.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.210.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.210.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.210.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.211.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.211.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.211.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.212.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.212.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.212.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.213.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.213.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.213.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.214.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.214.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.214.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.215.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.215.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.215.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.216.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.216.up_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.216.down_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.217.gate_proj.weight": "model-00025-of-000163.safetensors", + "model.layers.11.mlp.experts.217.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.217.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.218.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.218.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.218.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.219.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.219.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.219.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.220.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.220.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.220.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.221.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.221.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.221.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.222.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.222.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.222.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.223.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.223.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.223.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.224.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.224.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.224.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.225.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.225.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.225.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.226.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.226.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.226.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.227.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.227.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.227.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.228.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.228.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.228.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.229.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.229.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.229.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.230.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.230.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.230.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.231.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.231.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.231.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.232.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.232.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.232.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.233.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.233.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.233.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.234.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.234.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.234.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.235.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.235.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.235.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.236.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.236.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.236.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.237.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.237.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.237.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.238.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.238.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.238.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.239.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.239.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.239.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.240.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.240.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.240.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.241.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.241.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.241.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.242.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.242.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.242.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.243.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.243.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.243.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.244.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.244.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.244.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.245.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.245.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.245.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.246.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.246.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.246.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.247.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.247.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.247.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.248.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.248.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.248.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.249.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.249.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.249.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.250.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.250.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.250.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.251.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.251.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.251.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.252.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.252.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.252.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.253.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.253.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.253.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.254.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.254.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.254.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.255.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.255.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.mlp.experts.255.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.11.input_layernorm.weight": "model-00026-of-000163.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.q_a_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.q_a_layernorm.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.q_b_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.kv_b_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.indexer.wq_b.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.indexer.wk.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.indexer.k_norm.weight": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.indexer.k_norm.bias": "model-00026-of-000163.safetensors", + "model.layers.12.self_attn.indexer.weights_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.gate.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00026-of-000163.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.128.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.128.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.128.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.129.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.129.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.129.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.130.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.130.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.130.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.131.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.131.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.131.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.132.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.132.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.132.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.133.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.133.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.133.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.134.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.134.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.134.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.135.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.135.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.135.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.136.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.136.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.136.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.137.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.137.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.137.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.138.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.138.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.138.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.139.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.139.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.139.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.140.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.140.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.140.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.141.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.141.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.141.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.142.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.142.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.142.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.143.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.143.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.143.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.144.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.144.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.144.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.145.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.145.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.145.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.146.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.146.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.146.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.147.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.147.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.147.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.148.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.148.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.148.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.149.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.149.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.149.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.150.gate_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.150.up_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.150.down_proj.weight": "model-00027-of-000163.safetensors", + "model.layers.12.mlp.experts.151.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.151.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.151.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.152.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.152.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.152.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.153.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.153.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.153.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.154.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.154.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.154.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.155.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.155.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.155.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.156.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.156.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.156.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.157.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.157.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.157.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.158.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.158.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.158.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.159.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.159.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.159.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.160.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.160.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.160.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.161.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.161.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.161.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.162.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.162.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.162.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.163.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.163.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.163.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.164.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.164.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.164.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.165.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.165.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.165.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.166.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.166.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.166.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.167.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.167.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.167.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.168.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.168.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.168.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.169.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.169.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.169.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.170.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.170.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.170.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.171.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.171.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.171.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.172.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.172.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.172.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.173.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.173.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.173.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.174.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.174.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.174.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.175.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.175.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.175.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.176.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.176.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.176.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.177.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.177.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.177.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.178.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.178.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.178.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.179.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.179.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.179.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.180.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.180.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.180.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.181.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.181.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.181.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.182.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.182.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.182.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.183.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.183.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.183.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.184.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.184.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.184.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.185.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.185.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.185.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.186.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.186.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.186.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.187.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.187.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.187.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.188.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.188.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.188.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.189.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.189.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.189.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.190.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.190.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.190.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.191.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.191.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.191.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.192.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.192.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.192.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.193.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.193.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.193.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.194.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.194.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.194.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.195.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.195.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.195.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.196.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.196.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.196.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.197.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.197.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.197.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.198.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.198.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.198.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.199.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.199.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.199.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.200.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.200.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.200.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.201.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.201.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.201.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.202.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.202.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.202.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.203.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.203.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.203.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.204.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.204.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.204.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.205.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.205.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.205.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.206.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.206.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.206.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.207.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.207.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.207.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.208.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.208.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.208.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.209.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.209.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.209.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.210.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.210.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.210.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.211.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.211.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.211.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.212.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.212.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.212.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.213.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.213.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.213.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.214.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.214.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.214.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.215.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.215.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.215.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.216.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.216.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.216.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.217.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.217.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.217.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.218.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.218.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.218.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.219.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.219.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.219.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.220.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.220.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.220.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.221.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.221.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.221.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.222.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.222.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.222.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.223.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.223.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.223.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.224.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.224.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.224.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.225.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.225.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.225.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.226.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.226.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.226.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.227.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.227.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.227.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.228.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.228.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.228.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.229.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.229.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.229.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.230.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.230.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.230.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.231.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.231.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.231.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.232.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.232.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.232.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.233.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.233.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.233.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.234.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.234.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.234.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.235.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.235.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.235.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.236.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.236.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.236.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.237.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.237.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.237.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.238.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.238.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.238.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.239.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.239.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.239.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.240.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.240.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.240.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.241.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.241.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.241.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.242.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.242.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.242.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.243.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.243.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.243.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.244.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.244.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.244.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.245.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.245.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.245.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.246.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.246.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.246.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.247.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.247.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.247.down_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.248.gate_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.248.up_proj.weight": "model-00028-of-000163.safetensors", + "model.layers.12.mlp.experts.248.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.249.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.249.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.249.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.250.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.250.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.250.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.251.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.251.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.251.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.252.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.252.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.252.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.253.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.253.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.253.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.254.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.254.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.254.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.255.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.255.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.mlp.experts.255.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.12.input_layernorm.weight": "model-00029-of-000163.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.q_a_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.q_a_layernorm.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.q_b_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.kv_b_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.indexer.wq_b.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.indexer.wk.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.indexer.k_norm.weight": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.indexer.k_norm.bias": "model-00029-of-000163.safetensors", + "model.layers.13.self_attn.indexer.weights_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.gate.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00029-of-000163.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.128.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.128.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.128.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.129.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.129.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.129.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.130.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.130.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.130.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.131.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.131.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.131.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.132.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.132.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.132.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.133.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.133.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.133.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.134.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.134.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.134.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.135.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.135.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.135.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.136.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.136.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.136.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.137.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.137.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.137.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.138.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.138.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.138.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.139.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.139.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.139.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.140.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.140.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.140.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.141.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.141.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.141.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.142.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.142.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.142.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.143.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.143.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.143.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.144.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.144.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.144.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.145.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.145.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.145.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.146.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.146.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.146.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.147.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.147.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.147.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.148.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.148.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.148.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.149.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.149.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.149.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.150.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.150.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.150.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.151.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.151.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.151.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.152.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.152.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.152.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.153.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.153.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.153.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.154.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.154.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.154.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.155.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.155.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.155.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.156.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.156.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.156.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.157.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.157.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.157.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.158.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.158.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.158.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.159.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.159.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.159.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.160.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.160.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.160.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.161.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.161.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.161.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.162.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.162.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.162.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.163.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.163.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.163.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.164.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.164.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.164.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.165.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.165.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.165.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.166.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.166.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.166.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.167.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.167.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.167.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.168.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.168.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.168.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.169.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.169.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.169.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.170.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.170.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.170.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.171.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.171.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.171.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.172.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.172.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.172.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.173.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.173.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.173.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.174.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.174.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.174.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.175.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.175.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.175.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.176.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.176.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.176.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.177.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.177.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.177.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.178.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.178.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.178.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.179.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.179.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.179.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.180.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.180.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.180.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.181.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.181.up_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.181.down_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.182.gate_proj.weight": "model-00030-of-000163.safetensors", + "model.layers.13.mlp.experts.182.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.182.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.183.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.183.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.183.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.184.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.184.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.184.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.185.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.185.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.185.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.186.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.186.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.186.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.187.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.187.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.187.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.188.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.188.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.188.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.189.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.189.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.189.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.190.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.190.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.190.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.191.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.191.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.191.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.192.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.192.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.192.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.193.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.193.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.193.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.194.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.194.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.194.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.195.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.195.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.195.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.196.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.196.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.196.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.197.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.197.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.197.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.198.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.198.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.198.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.199.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.199.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.199.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.200.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.200.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.200.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.201.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.201.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.201.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.202.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.202.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.202.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.203.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.203.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.203.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.204.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.204.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.204.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.205.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.205.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.205.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.206.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.206.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.206.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.207.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.207.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.207.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.208.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.208.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.208.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.209.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.209.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.209.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.210.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.210.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.210.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.211.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.211.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.211.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.212.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.212.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.212.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.213.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.213.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.213.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.214.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.214.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.214.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.215.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.215.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.215.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.216.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.216.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.216.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.217.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.217.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.217.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.218.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.218.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.218.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.219.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.219.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.219.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.220.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.220.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.220.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.221.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.221.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.221.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.222.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.222.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.222.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.223.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.223.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.223.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.224.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.224.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.224.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.225.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.225.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.225.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.226.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.226.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.226.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.227.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.227.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.227.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.228.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.228.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.228.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.229.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.229.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.229.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.230.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.230.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.230.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.231.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.231.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.231.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.232.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.232.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.232.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.233.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.233.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.233.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.234.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.234.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.234.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.235.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.235.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.235.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.236.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.236.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.236.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.237.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.237.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.237.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.238.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.238.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.238.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.239.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.239.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.239.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.240.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.240.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.240.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.241.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.241.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.241.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.242.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.242.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.242.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.243.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.243.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.243.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.244.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.244.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.244.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.245.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.245.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.245.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.246.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.246.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.246.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.247.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.247.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.247.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.248.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.248.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.248.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.249.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.249.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.249.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.250.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.250.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.250.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.251.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.251.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.251.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.252.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.252.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.252.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.253.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.253.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.253.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.254.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.254.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.254.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.255.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.255.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.mlp.experts.255.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.13.input_layernorm.weight": "model-00031-of-000163.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.q_a_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.q_a_layernorm.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.q_b_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.kv_b_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.indexer.wq_b.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.indexer.wk.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.indexer.k_norm.weight": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.indexer.k_norm.bias": "model-00031-of-000163.safetensors", + "model.layers.14.self_attn.indexer.weights_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.gate.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00031-of-000163.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00032-of-000163.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.128.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.128.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.128.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.129.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.129.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.129.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.130.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.130.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.130.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.131.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.131.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.131.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.132.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.132.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.132.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.133.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.133.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.133.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.134.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.134.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.134.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.135.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.135.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.135.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.136.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.136.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.136.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.137.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.137.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.137.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.138.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.138.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.138.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.139.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.139.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.139.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.140.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.140.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.140.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.141.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.141.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.141.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.142.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.142.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.142.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.143.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.143.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.143.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.144.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.144.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.144.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.145.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.145.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.145.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.146.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.146.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.146.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.147.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.147.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.147.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.148.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.148.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.148.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.149.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.149.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.149.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.150.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.150.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.150.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.151.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.151.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.151.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.152.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.152.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.152.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.153.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.153.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.153.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.154.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.154.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.154.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.155.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.155.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.155.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.156.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.156.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.156.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.157.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.157.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.157.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.158.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.158.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.158.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.159.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.159.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.159.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.160.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.160.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.160.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.161.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.161.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.161.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.162.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.162.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.162.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.163.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.163.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.163.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.164.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.164.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.164.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.165.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.165.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.165.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.166.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.166.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.166.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.167.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.167.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.167.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.168.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.168.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.168.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.169.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.169.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.169.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.170.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.170.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.170.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.171.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.171.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.171.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.172.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.172.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.172.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.173.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.173.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.173.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.174.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.174.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.174.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.175.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.175.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.175.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.176.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.176.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.176.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.177.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.177.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.177.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.178.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.178.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.178.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.179.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.179.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.179.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.180.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.180.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.180.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.181.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.181.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.181.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.182.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.182.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.182.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.183.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.183.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.183.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.184.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.184.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.184.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.185.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.185.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.185.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.186.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.186.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.186.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.187.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.187.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.187.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.188.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.188.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.188.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.189.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.189.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.189.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.190.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.190.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.190.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.191.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.191.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.191.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.192.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.192.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.192.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.193.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.193.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.193.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.194.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.194.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.194.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.195.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.195.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.195.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.196.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.196.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.196.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.197.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.197.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.197.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.198.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.198.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.198.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.199.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.199.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.199.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.200.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.200.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.200.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.201.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.201.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.201.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.202.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.202.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.202.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.203.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.203.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.203.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.204.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.204.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.204.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.205.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.205.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.205.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.206.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.206.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.206.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.207.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.207.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.207.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.208.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.208.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.208.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.209.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.209.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.209.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.210.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.210.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.210.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.211.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.211.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.211.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.212.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.212.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.212.down_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.213.gate_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.213.up_proj.weight": "model-00033-of-000163.safetensors", + "model.layers.14.mlp.experts.213.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.214.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.214.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.214.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.215.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.215.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.215.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.216.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.216.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.216.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.217.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.217.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.217.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.218.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.218.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.218.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.219.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.219.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.219.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.220.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.220.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.220.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.221.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.221.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.221.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.222.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.222.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.222.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.223.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.223.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.223.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.224.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.224.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.224.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.225.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.225.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.225.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.226.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.226.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.226.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.227.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.227.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.227.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.228.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.228.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.228.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.229.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.229.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.229.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.230.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.230.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.230.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.231.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.231.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.231.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.232.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.232.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.232.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.233.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.233.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.233.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.234.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.234.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.234.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.235.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.235.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.235.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.236.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.236.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.236.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.237.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.237.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.237.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.238.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.238.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.238.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.239.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.239.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.239.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.240.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.240.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.240.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.241.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.241.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.241.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.242.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.242.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.242.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.243.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.243.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.243.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.244.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.244.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.244.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.245.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.245.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.245.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.246.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.246.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.246.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.247.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.247.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.247.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.248.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.248.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.248.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.249.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.249.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.249.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.250.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.250.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.250.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.251.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.251.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.251.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.252.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.252.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.252.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.253.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.253.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.253.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.254.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.254.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.254.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.255.gate_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.255.up_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.mlp.experts.255.down_proj.weight": "model-00034-of-000163.safetensors", + "model.layers.14.input_layernorm.weight": "model-00034-of-000163.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00034-of-000163.safetensors", + "model.layers.15.self_attn.q_a_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.q_a_layernorm.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.q_b_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.kv_b_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.indexer.wq_b.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.indexer.wk.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.indexer.k_norm.weight": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.indexer.k_norm.bias": "model-00035-of-000163.safetensors", + "model.layers.15.self_attn.indexer.weights_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.gate.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00035-of-000163.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.128.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.128.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.128.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.129.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.129.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.129.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.130.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.130.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.130.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.131.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.131.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.131.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.132.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.132.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.132.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.133.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.133.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.133.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.134.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.134.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.134.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.135.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.135.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.135.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.136.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.136.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.136.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.137.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.137.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.137.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.138.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.138.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.138.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.139.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.139.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.139.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.140.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.140.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.140.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.141.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.141.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.141.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.142.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.142.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.142.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.143.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.143.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.143.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.144.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.144.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.144.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.145.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.145.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.145.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.146.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.146.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.146.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.147.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.147.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.147.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.148.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.148.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.148.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.149.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.149.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.149.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.150.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.150.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.150.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.151.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.151.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.151.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.152.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.152.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.152.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.153.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.153.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.153.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.154.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.154.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.154.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.155.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.155.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.155.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.156.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.156.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.156.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.157.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.157.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.157.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.158.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.158.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.158.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.159.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.159.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.159.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.160.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.160.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.160.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.161.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.161.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.161.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.162.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.162.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.162.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.163.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.163.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.163.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.164.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.164.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.164.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.165.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.165.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.165.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.166.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.166.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.166.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.167.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.167.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.167.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.168.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.168.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.168.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.169.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.169.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.169.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.170.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.170.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.170.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.171.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.171.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.171.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.172.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.172.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.172.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.173.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.173.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.173.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.174.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.174.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.174.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.175.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.175.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.175.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.176.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.176.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.176.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.177.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.177.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.177.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.178.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.178.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.178.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.179.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.179.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.179.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.180.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.180.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.180.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.181.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.181.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.181.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.182.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.182.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.182.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.183.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.183.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.183.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.184.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.184.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.184.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.185.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.185.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.185.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.186.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.186.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.186.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.187.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.187.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.187.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.188.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.188.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.188.down_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.189.gate_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.189.up_proj.weight": "model-00036-of-000163.safetensors", + "model.layers.15.mlp.experts.189.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.190.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.190.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.190.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.191.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.191.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.191.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.192.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.192.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.192.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.193.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.193.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.193.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.194.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.194.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.194.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.195.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.195.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.195.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.196.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.196.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.196.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.197.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.197.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.197.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.198.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.198.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.198.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.199.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.199.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.199.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.200.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.200.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.200.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.201.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.201.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.201.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.202.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.202.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.202.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.203.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.203.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.203.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.204.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.204.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.204.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.205.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.205.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.205.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.206.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.206.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.206.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.207.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.207.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.207.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.208.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.208.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.208.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.209.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.209.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.209.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.210.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.210.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.210.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.211.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.211.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.211.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.212.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.212.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.212.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.213.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.213.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.213.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.214.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.214.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.214.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.215.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.215.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.215.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.216.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.216.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.216.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.217.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.217.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.217.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.218.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.218.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.218.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.219.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.219.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.219.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.220.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.220.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.220.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.221.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.221.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.221.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.222.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.222.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.222.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.223.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.223.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.223.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.224.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.224.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.224.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.225.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.225.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.225.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.226.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.226.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.226.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.227.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.227.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.227.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.228.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.228.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.228.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.229.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.229.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.229.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.230.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.230.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.230.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.231.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.231.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.231.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.232.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.232.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.232.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.233.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.233.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.233.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.234.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.234.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.234.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.235.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.235.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.235.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.236.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.236.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.236.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.237.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.237.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.237.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.238.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.238.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.238.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.239.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.239.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.239.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.240.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.240.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.240.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.241.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.241.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.241.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.242.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.242.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.242.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.243.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.243.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.243.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.244.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.244.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.244.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.245.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.245.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.245.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.246.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.246.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.246.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.247.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.247.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.247.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.248.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.248.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.248.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.249.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.249.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.249.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.250.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.250.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.250.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.251.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.251.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.251.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.252.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.252.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.252.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.253.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.253.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.253.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.254.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.254.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.254.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.255.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.255.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.mlp.experts.255.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.15.input_layernorm.weight": "model-00037-of-000163.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.q_a_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.q_a_layernorm.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.q_b_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.kv_b_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.indexer.wq_b.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.indexer.wk.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.indexer.k_norm.weight": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.indexer.k_norm.bias": "model-00037-of-000163.safetensors", + "model.layers.16.self_attn.indexer.weights_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.gate.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00037-of-000163.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00038-of-000163.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.128.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.128.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.128.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.129.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.129.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.129.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.130.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.130.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.130.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.131.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.131.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.131.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.132.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.132.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.132.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.133.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.133.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.133.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.134.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.134.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.134.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.135.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.135.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.135.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.136.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.136.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.136.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.137.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.137.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.137.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.138.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.138.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.138.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.139.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.139.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.139.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.140.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.140.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.140.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.141.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.141.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.141.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.142.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.142.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.142.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.143.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.143.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.143.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.144.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.144.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.144.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.145.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.145.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.145.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.146.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.146.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.146.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.147.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.147.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.147.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.148.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.148.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.148.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.149.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.149.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.149.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.150.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.150.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.150.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.151.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.151.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.151.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.152.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.152.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.152.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.153.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.153.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.153.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.154.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.154.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.154.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.155.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.155.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.155.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.156.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.156.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.156.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.157.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.157.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.157.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.158.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.158.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.158.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.159.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.159.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.159.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.160.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.160.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.160.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.161.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.161.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.161.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.162.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.162.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.162.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.163.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.163.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.163.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.164.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.164.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.164.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.165.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.165.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.165.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.166.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.166.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.166.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.167.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.167.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.167.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.168.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.168.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.168.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.169.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.169.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.169.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.170.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.170.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.170.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.171.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.171.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.171.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.172.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.172.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.172.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.173.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.173.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.173.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.174.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.174.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.174.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.175.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.175.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.175.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.176.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.176.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.176.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.177.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.177.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.177.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.178.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.178.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.178.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.179.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.179.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.179.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.180.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.180.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.180.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.181.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.181.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.181.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.182.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.182.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.182.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.183.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.183.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.183.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.184.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.184.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.184.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.185.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.185.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.185.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.186.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.186.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.186.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.187.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.187.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.187.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.188.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.188.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.188.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.189.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.189.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.189.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.190.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.190.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.190.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.191.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.191.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.191.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.192.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.192.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.192.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.193.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.193.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.193.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.194.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.194.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.194.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.195.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.195.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.195.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.196.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.196.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.196.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.197.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.197.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.197.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.198.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.198.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.198.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.199.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.199.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.199.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.200.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.200.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.200.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.201.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.201.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.201.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.202.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.202.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.202.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.203.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.203.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.203.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.204.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.204.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.204.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.205.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.205.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.205.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.206.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.206.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.206.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.207.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.207.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.207.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.208.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.208.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.208.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.209.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.209.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.209.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.210.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.210.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.210.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.211.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.211.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.211.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.212.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.212.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.212.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.213.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.213.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.213.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.214.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.214.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.214.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.215.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.215.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.215.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.216.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.216.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.216.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.217.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.217.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.217.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.218.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.218.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.218.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.219.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.219.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.219.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.220.gate_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.220.up_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.220.down_proj.weight": "model-00039-of-000163.safetensors", + "model.layers.16.mlp.experts.221.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.221.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.221.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.222.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.222.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.222.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.223.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.223.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.223.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.224.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.224.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.224.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.225.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.225.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.225.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.226.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.226.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.226.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.227.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.227.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.227.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.228.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.228.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.228.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.229.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.229.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.229.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.230.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.230.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.230.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.231.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.231.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.231.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.232.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.232.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.232.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.233.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.233.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.233.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.234.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.234.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.234.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.235.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.235.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.235.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.236.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.236.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.236.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.237.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.237.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.237.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.238.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.238.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.238.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.239.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.239.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.239.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.240.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.240.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.240.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.241.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.241.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.241.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.242.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.242.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.242.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.243.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.243.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.243.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.244.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.244.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.244.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.245.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.245.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.245.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.246.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.246.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.246.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.247.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.247.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.247.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.248.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.248.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.248.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.249.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.249.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.249.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.250.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.250.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.250.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.251.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.251.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.251.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.252.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.252.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.252.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.253.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.253.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.253.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.254.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.254.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.254.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.255.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.255.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.mlp.experts.255.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.16.input_layernorm.weight": "model-00040-of-000163.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.q_a_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.q_a_layernorm.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.q_b_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.kv_b_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.indexer.wq_b.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.indexer.wk.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.indexer.k_norm.weight": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.indexer.k_norm.bias": "model-00040-of-000163.safetensors", + "model.layers.17.self_attn.indexer.weights_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.gate.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00040-of-000163.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.128.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.128.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.128.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.129.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.129.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.129.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.130.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.130.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.130.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.131.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.131.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.131.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.132.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.132.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.132.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.133.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.133.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.133.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.134.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.134.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.134.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.135.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.135.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.135.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.136.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.136.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.136.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.137.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.137.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.137.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.138.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.138.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.138.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.139.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.139.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.139.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.140.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.140.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.140.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.141.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.141.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.141.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.142.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.142.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.142.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.143.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.143.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.143.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.144.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.144.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.144.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.145.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.145.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.145.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.146.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.146.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.146.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.147.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.147.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.147.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.148.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.148.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.148.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.149.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.149.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.149.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.150.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.150.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.150.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.151.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.151.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.151.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.152.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.152.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.152.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.153.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.153.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.153.down_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.154.gate_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.154.up_proj.weight": "model-00041-of-000163.safetensors", + "model.layers.17.mlp.experts.154.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.155.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.155.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.155.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.156.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.156.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.156.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.157.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.157.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.157.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.158.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.158.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.158.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.159.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.159.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.159.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.160.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.160.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.160.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.161.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.161.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.161.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.162.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.162.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.162.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.163.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.163.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.163.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.164.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.164.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.164.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.165.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.165.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.165.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.166.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.166.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.166.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.167.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.167.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.167.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.168.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.168.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.168.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.169.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.169.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.169.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.170.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.170.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.170.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.171.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.171.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.171.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.172.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.172.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.172.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.173.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.173.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.173.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.174.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.174.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.174.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.175.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.175.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.175.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.176.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.176.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.176.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.177.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.177.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.177.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.178.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.178.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.178.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.179.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.179.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.179.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.180.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.180.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.180.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.181.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.181.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.181.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.182.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.182.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.182.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.183.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.183.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.183.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.184.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.184.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.184.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.185.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.185.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.185.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.186.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.186.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.186.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.187.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.187.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.187.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.188.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.188.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.188.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.189.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.189.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.189.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.190.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.190.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.190.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.191.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.191.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.191.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.192.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.192.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.192.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.193.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.193.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.193.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.194.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.194.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.194.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.195.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.195.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.195.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.196.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.196.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.196.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.197.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.197.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.197.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.198.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.198.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.198.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.199.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.199.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.199.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.200.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.200.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.200.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.201.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.201.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.201.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.202.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.202.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.202.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.203.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.203.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.203.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.204.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.204.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.204.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.205.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.205.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.205.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.206.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.206.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.206.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.207.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.207.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.207.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.208.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.208.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.208.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.209.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.209.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.209.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.210.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.210.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.210.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.211.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.211.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.211.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.212.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.212.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.212.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.213.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.213.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.213.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.214.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.214.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.214.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.215.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.215.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.215.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.216.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.216.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.216.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.217.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.217.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.217.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.218.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.218.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.218.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.219.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.219.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.219.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.220.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.220.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.220.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.221.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.221.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.221.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.222.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.222.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.222.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.223.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.223.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.223.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.224.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.224.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.224.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.225.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.225.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.225.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.226.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.226.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.226.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.227.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.227.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.227.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.228.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.228.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.228.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.229.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.229.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.229.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.230.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.230.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.230.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.231.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.231.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.231.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.232.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.232.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.232.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.233.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.233.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.233.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.234.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.234.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.234.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.235.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.235.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.235.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.236.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.236.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.236.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.237.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.237.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.237.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.238.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.238.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.238.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.239.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.239.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.239.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.240.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.240.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.240.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.241.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.241.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.241.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.242.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.242.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.242.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.243.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.243.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.243.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.244.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.244.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.244.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.245.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.245.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.245.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.246.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.246.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.246.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.247.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.247.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.247.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.248.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.248.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.248.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.249.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.249.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.249.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.250.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.250.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.250.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.251.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.251.up_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.251.down_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.252.gate_proj.weight": "model-00042-of-000163.safetensors", + "model.layers.17.mlp.experts.252.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.252.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.253.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.253.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.253.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.254.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.254.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.254.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.255.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.255.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.mlp.experts.255.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.17.input_layernorm.weight": "model-00043-of-000163.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.q_a_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.q_a_layernorm.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.q_b_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.kv_b_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.indexer.wq_b.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.indexer.wk.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.indexer.k_norm.weight": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.indexer.k_norm.bias": "model-00043-of-000163.safetensors", + "model.layers.18.self_attn.indexer.weights_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.gate.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00043-of-000163.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.128.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.128.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.128.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.129.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.129.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.129.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.130.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.130.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.130.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.131.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.131.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.131.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.132.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.132.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.132.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.133.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.133.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.133.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.134.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.134.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.134.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.135.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.135.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.135.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.136.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.136.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.136.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.137.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.137.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.137.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.138.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.138.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.138.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.139.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.139.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.139.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.140.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.140.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.140.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.141.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.141.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.141.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.142.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.142.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.142.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.143.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.143.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.143.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.144.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.144.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.144.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.145.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.145.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.145.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.146.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.146.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.146.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.147.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.147.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.147.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.148.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.148.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.148.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.149.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.149.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.149.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.150.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.150.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.150.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.151.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.151.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.151.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.152.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.152.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.152.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.153.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.153.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.153.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.154.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.154.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.154.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.155.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.155.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.155.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.156.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.156.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.156.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.157.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.157.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.157.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.158.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.158.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.158.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.159.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.159.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.159.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.160.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.160.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.160.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.161.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.161.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.161.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.162.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.162.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.162.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.163.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.163.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.163.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.164.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.164.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.164.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.165.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.165.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.165.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.166.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.166.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.166.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.167.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.167.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.167.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.168.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.168.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.168.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.169.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.169.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.169.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.170.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.170.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.170.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.171.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.171.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.171.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.172.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.172.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.172.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.173.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.173.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.173.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.174.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.174.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.174.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.175.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.175.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.175.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.176.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.176.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.176.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.177.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.177.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.177.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.178.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.178.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.178.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.179.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.179.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.179.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.180.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.180.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.180.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.181.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.181.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.181.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.182.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.182.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.182.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.183.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.183.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.183.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.184.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.184.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.184.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.185.gate_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.185.up_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.185.down_proj.weight": "model-00044-of-000163.safetensors", + "model.layers.18.mlp.experts.186.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.186.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.186.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.187.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.187.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.187.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.188.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.188.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.188.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.189.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.189.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.189.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.190.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.190.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.190.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.191.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.191.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.191.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.192.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.192.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.192.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.193.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.193.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.193.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.194.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.194.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.194.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.195.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.195.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.195.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.196.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.196.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.196.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.197.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.197.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.197.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.198.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.198.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.198.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.199.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.199.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.199.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.200.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.200.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.200.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.201.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.201.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.201.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.202.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.202.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.202.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.203.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.203.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.203.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.204.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.204.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.204.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.205.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.205.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.205.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.206.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.206.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.206.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.207.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.207.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.207.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.208.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.208.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.208.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.209.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.209.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.209.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.210.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.210.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.210.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.211.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.211.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.211.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.212.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.212.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.212.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.213.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.213.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.213.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.214.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.214.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.214.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.215.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.215.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.215.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.216.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.216.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.216.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.217.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.217.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.217.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.218.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.218.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.218.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.219.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.219.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.219.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.220.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.220.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.220.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.221.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.221.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.221.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.222.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.222.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.222.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.223.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.223.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.223.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.224.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.224.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.224.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.225.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.225.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.225.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.226.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.226.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.226.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.227.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.227.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.227.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.228.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.228.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.228.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.229.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.229.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.229.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.230.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.230.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.230.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.231.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.231.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.231.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.232.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.232.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.232.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.233.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.233.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.233.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.234.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.234.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.234.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.235.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.235.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.235.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.236.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.236.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.236.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.237.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.237.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.237.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.238.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.238.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.238.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.239.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.239.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.239.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.240.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.240.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.240.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.241.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.241.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.241.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.242.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.242.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.242.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.243.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.243.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.243.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.244.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.244.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.244.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.245.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.245.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.245.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.246.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.246.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.246.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.247.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.247.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.247.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.248.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.248.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.248.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.249.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.249.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.249.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.250.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.250.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.250.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.251.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.251.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.251.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.252.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.252.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.252.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.253.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.253.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.253.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.254.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.254.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.254.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.255.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.255.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.mlp.experts.255.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.18.input_layernorm.weight": "model-00045-of-000163.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.q_a_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.q_a_layernorm.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.q_b_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.kv_b_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.indexer.wq_b.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.indexer.wk.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.indexer.k_norm.weight": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.indexer.k_norm.bias": "model-00045-of-000163.safetensors", + "model.layers.19.self_attn.indexer.weights_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.gate.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00045-of-000163.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00046-of-000163.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.128.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.128.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.128.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.129.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.129.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.129.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.130.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.130.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.130.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.131.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.131.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.131.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.132.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.132.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.132.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.133.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.133.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.133.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.134.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.134.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.134.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.135.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.135.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.135.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.136.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.136.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.136.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.137.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.137.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.137.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.138.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.138.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.138.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.139.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.139.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.139.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.140.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.140.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.140.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.141.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.141.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.141.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.142.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.142.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.142.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.143.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.143.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.143.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.144.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.144.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.144.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.145.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.145.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.145.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.146.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.146.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.146.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.147.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.147.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.147.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.148.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.148.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.148.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.149.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.149.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.149.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.150.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.150.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.150.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.151.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.151.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.151.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.152.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.152.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.152.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.153.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.153.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.153.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.154.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.154.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.154.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.155.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.155.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.155.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.156.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.156.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.156.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.157.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.157.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.157.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.158.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.158.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.158.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.159.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.159.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.159.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.160.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.160.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.160.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.161.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.161.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.161.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.162.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.162.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.162.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.163.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.163.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.163.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.164.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.164.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.164.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.165.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.165.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.165.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.166.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.166.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.166.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.167.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.167.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.167.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.168.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.168.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.168.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.169.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.169.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.169.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.170.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.170.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.170.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.171.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.171.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.171.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.172.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.172.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.172.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.173.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.173.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.173.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.174.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.174.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.174.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.175.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.175.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.175.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.176.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.176.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.176.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.177.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.177.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.177.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.178.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.178.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.178.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.179.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.179.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.179.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.180.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.180.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.180.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.181.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.181.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.181.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.182.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.182.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.182.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.183.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.183.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.183.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.184.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.184.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.184.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.185.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.185.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.185.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.186.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.186.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.186.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.187.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.187.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.187.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.188.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.188.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.188.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.189.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.189.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.189.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.190.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.190.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.190.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.191.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.191.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.191.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.192.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.192.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.192.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.193.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.193.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.193.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.194.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.194.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.194.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.195.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.195.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.195.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.196.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.196.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.196.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.197.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.197.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.197.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.198.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.198.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.198.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.199.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.199.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.199.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.200.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.200.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.200.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.201.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.201.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.201.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.202.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.202.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.202.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.203.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.203.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.203.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.204.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.204.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.204.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.205.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.205.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.205.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.206.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.206.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.206.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.207.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.207.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.207.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.208.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.208.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.208.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.209.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.209.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.209.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.210.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.210.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.210.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.211.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.211.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.211.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.212.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.212.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.212.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.213.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.213.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.213.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.214.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.214.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.214.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.215.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.215.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.215.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.216.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.216.up_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.216.down_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.217.gate_proj.weight": "model-00047-of-000163.safetensors", + "model.layers.19.mlp.experts.217.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.217.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.218.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.218.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.218.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.219.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.219.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.219.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.220.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.220.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.220.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.221.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.221.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.221.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.222.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.222.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.222.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.223.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.223.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.223.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.224.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.224.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.224.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.225.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.225.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.225.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.226.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.226.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.226.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.227.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.227.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.227.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.228.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.228.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.228.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.229.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.229.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.229.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.230.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.230.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.230.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.231.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.231.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.231.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.232.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.232.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.232.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.233.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.233.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.233.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.234.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.234.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.234.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.235.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.235.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.235.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.236.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.236.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.236.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.237.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.237.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.237.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.238.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.238.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.238.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.239.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.239.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.239.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.240.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.240.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.240.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.241.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.241.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.241.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.242.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.242.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.242.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.243.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.243.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.243.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.244.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.244.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.244.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.245.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.245.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.245.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.246.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.246.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.246.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.247.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.247.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.247.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.248.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.248.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.248.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.249.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.249.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.249.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.250.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.250.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.250.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.251.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.251.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.251.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.252.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.252.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.252.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.253.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.253.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.253.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.254.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.254.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.254.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.255.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.255.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.mlp.experts.255.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.19.input_layernorm.weight": "model-00048-of-000163.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.q_a_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.q_a_layernorm.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.q_b_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.kv_b_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.indexer.wq_b.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.indexer.wk.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.indexer.k_norm.weight": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.indexer.k_norm.bias": "model-00048-of-000163.safetensors", + "model.layers.20.self_attn.indexer.weights_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.gate.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00048-of-000163.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.128.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.128.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.128.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.129.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.129.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.129.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.130.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.130.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.130.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.131.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.131.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.131.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.132.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.132.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.132.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.133.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.133.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.133.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.134.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.134.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.134.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.135.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.135.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.135.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.136.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.136.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.136.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.137.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.137.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.137.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.138.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.138.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.138.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.139.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.139.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.139.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.140.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.140.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.140.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.141.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.141.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.141.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.142.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.142.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.142.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.143.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.143.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.143.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.144.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.144.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.144.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.145.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.145.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.145.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.146.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.146.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.146.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.147.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.147.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.147.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.148.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.148.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.148.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.149.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.149.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.149.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.150.gate_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.150.up_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.150.down_proj.weight": "model-00049-of-000163.safetensors", + "model.layers.20.mlp.experts.151.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.151.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.151.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.152.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.152.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.152.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.153.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.153.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.153.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.154.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.154.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.154.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.155.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.155.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.155.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.156.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.156.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.156.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.157.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.157.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.157.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.158.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.158.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.158.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.159.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.159.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.159.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.160.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.160.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.160.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.161.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.161.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.161.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.162.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.162.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.162.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.163.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.163.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.163.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.164.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.164.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.164.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.165.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.165.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.165.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.166.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.166.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.166.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.167.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.167.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.167.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.168.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.168.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.168.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.169.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.169.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.169.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.170.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.170.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.170.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.171.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.171.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.171.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.172.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.172.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.172.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.173.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.173.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.173.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.174.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.174.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.174.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.175.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.175.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.175.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.176.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.176.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.176.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.177.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.177.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.177.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.178.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.178.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.178.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.179.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.179.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.179.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.180.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.180.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.180.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.181.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.181.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.181.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.182.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.182.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.182.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.183.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.183.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.183.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.184.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.184.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.184.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.185.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.185.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.185.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.186.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.186.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.186.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.187.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.187.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.187.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.188.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.188.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.188.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.189.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.189.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.189.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.190.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.190.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.190.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.191.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.191.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.191.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.192.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.192.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.192.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.193.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.193.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.193.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.194.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.194.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.194.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.195.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.195.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.195.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.196.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.196.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.196.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.197.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.197.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.197.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.198.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.198.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.198.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.199.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.199.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.199.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.200.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.200.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.200.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.201.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.201.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.201.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.202.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.202.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.202.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.203.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.203.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.203.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.204.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.204.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.204.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.205.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.205.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.205.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.206.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.206.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.206.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.207.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.207.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.207.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.208.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.208.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.208.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.209.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.209.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.209.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.210.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.210.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.210.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.211.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.211.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.211.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.212.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.212.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.212.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.213.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.213.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.213.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.214.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.214.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.214.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.215.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.215.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.215.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.216.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.216.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.216.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.217.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.217.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.217.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.218.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.218.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.218.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.219.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.219.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.219.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.220.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.220.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.220.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.221.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.221.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.221.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.222.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.222.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.222.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.223.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.223.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.223.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.224.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.224.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.224.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.225.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.225.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.225.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.226.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.226.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.226.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.227.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.227.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.227.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.228.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.228.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.228.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.229.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.229.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.229.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.230.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.230.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.230.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.231.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.231.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.231.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.232.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.232.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.232.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.233.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.233.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.233.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.234.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.234.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.234.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.235.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.235.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.235.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.236.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.236.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.236.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.237.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.237.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.237.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.238.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.238.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.238.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.239.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.239.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.239.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.240.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.240.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.240.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.241.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.241.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.241.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.242.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.242.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.242.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.243.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.243.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.243.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.244.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.244.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.244.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.245.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.245.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.245.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.246.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.246.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.246.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.247.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.247.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.247.down_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.248.gate_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.248.up_proj.weight": "model-00050-of-000163.safetensors", + "model.layers.20.mlp.experts.248.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.249.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.249.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.249.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.250.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.250.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.250.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.251.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.251.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.251.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.252.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.252.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.252.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.253.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.253.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.253.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.254.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.254.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.254.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.255.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.255.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.mlp.experts.255.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.20.input_layernorm.weight": "model-00051-of-000163.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.q_a_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.q_a_layernorm.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.q_b_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.kv_b_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.indexer.wq_b.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.indexer.wk.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.indexer.k_norm.weight": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.indexer.k_norm.bias": "model-00051-of-000163.safetensors", + "model.layers.21.self_attn.indexer.weights_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.gate.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00051-of-000163.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.128.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.128.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.128.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.129.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.129.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.129.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.130.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.130.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.130.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.131.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.131.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.131.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.132.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.132.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.132.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.133.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.133.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.133.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.134.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.134.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.134.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.135.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.135.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.135.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.136.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.136.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.136.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.137.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.137.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.137.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.138.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.138.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.138.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.139.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.139.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.139.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.140.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.140.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.140.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.141.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.141.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.141.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.142.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.142.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.142.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.143.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.143.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.143.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.144.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.144.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.144.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.145.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.145.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.145.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.146.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.146.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.146.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.147.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.147.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.147.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.148.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.148.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.148.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.149.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.149.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.149.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.150.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.150.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.150.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.151.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.151.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.151.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.152.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.152.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.152.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.153.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.153.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.153.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.154.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.154.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.154.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.155.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.155.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.155.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.156.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.156.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.156.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.157.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.157.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.157.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.158.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.158.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.158.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.159.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.159.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.159.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.160.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.160.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.160.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.161.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.161.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.161.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.162.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.162.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.162.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.163.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.163.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.163.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.164.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.164.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.164.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.165.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.165.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.165.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.166.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.166.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.166.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.167.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.167.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.167.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.168.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.168.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.168.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.169.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.169.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.169.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.170.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.170.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.170.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.171.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.171.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.171.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.172.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.172.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.172.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.173.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.173.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.173.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.174.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.174.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.174.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.175.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.175.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.175.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.176.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.176.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.176.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.177.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.177.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.177.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.178.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.178.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.178.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.179.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.179.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.179.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.180.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.180.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.180.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.181.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.181.up_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.181.down_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.182.gate_proj.weight": "model-00052-of-000163.safetensors", + "model.layers.21.mlp.experts.182.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.182.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.183.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.183.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.183.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.184.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.184.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.184.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.185.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.185.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.185.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.186.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.186.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.186.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.187.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.187.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.187.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.188.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.188.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.188.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.189.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.189.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.189.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.190.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.190.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.190.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.191.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.191.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.191.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.192.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.192.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.192.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.193.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.193.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.193.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.194.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.194.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.194.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.195.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.195.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.195.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.196.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.196.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.196.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.197.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.197.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.197.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.198.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.198.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.198.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.199.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.199.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.199.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.200.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.200.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.200.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.201.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.201.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.201.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.202.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.202.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.202.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.203.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.203.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.203.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.204.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.204.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.204.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.205.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.205.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.205.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.206.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.206.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.206.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.207.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.207.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.207.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.208.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.208.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.208.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.209.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.209.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.209.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.210.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.210.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.210.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.211.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.211.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.211.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.212.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.212.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.212.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.213.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.213.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.213.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.214.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.214.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.214.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.215.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.215.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.215.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.216.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.216.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.216.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.217.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.217.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.217.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.218.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.218.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.218.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.219.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.219.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.219.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.220.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.220.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.220.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.221.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.221.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.221.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.222.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.222.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.222.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.223.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.223.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.223.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.224.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.224.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.224.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.225.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.225.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.225.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.226.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.226.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.226.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.227.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.227.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.227.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.228.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.228.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.228.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.229.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.229.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.229.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.230.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.230.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.230.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.231.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.231.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.231.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.232.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.232.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.232.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.233.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.233.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.233.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.234.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.234.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.234.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.235.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.235.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.235.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.236.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.236.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.236.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.237.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.237.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.237.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.238.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.238.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.238.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.239.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.239.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.239.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.240.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.240.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.240.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.241.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.241.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.241.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.242.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.242.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.242.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.243.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.243.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.243.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.244.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.244.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.244.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.245.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.245.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.245.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.246.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.246.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.246.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.247.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.247.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.247.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.248.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.248.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.248.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.249.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.249.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.249.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.250.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.250.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.250.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.251.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.251.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.251.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.252.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.252.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.252.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.253.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.253.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.253.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.254.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.254.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.254.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.255.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.255.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.mlp.experts.255.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.21.input_layernorm.weight": "model-00053-of-000163.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.q_a_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.q_a_layernorm.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.q_b_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.kv_b_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.indexer.wq_b.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.indexer.wk.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.indexer.k_norm.weight": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.indexer.k_norm.bias": "model-00053-of-000163.safetensors", + "model.layers.22.self_attn.indexer.weights_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.gate.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00053-of-000163.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00054-of-000163.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.128.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.128.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.128.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.129.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.129.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.129.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.130.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.130.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.130.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.131.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.131.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.131.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.132.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.132.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.132.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.133.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.133.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.133.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.134.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.134.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.134.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.135.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.135.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.135.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.136.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.136.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.136.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.137.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.137.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.137.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.138.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.138.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.138.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.139.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.139.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.139.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.140.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.140.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.140.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.141.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.141.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.141.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.142.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.142.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.142.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.143.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.143.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.143.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.144.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.144.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.144.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.145.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.145.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.145.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.146.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.146.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.146.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.147.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.147.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.147.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.148.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.148.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.148.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.149.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.149.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.149.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.150.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.150.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.150.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.151.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.151.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.151.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.152.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.152.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.152.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.153.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.153.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.153.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.154.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.154.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.154.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.155.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.155.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.155.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.156.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.156.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.156.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.157.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.157.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.157.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.158.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.158.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.158.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.159.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.159.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.159.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.160.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.160.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.160.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.161.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.161.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.161.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.162.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.162.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.162.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.163.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.163.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.163.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.164.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.164.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.164.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.165.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.165.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.165.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.166.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.166.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.166.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.167.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.167.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.167.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.168.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.168.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.168.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.169.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.169.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.169.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.170.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.170.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.170.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.171.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.171.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.171.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.172.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.172.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.172.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.173.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.173.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.173.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.174.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.174.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.174.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.175.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.175.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.175.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.176.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.176.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.176.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.177.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.177.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.177.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.178.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.178.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.178.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.179.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.179.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.179.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.180.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.180.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.180.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.181.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.181.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.181.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.182.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.182.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.182.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.183.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.183.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.183.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.184.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.184.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.184.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.185.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.185.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.185.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.186.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.186.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.186.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.187.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.187.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.187.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.188.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.188.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.188.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.189.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.189.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.189.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.190.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.190.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.190.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.191.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.191.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.191.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.192.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.192.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.192.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.193.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.193.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.193.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.194.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.194.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.194.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.195.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.195.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.195.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.196.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.196.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.196.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.197.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.197.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.197.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.198.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.198.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.198.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.199.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.199.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.199.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.200.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.200.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.200.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.201.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.201.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.201.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.202.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.202.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.202.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.203.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.203.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.203.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.204.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.204.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.204.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.205.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.205.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.205.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.206.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.206.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.206.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.207.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.207.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.207.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.208.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.208.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.208.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.209.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.209.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.209.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.210.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.210.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.210.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.211.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.211.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.211.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.212.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.212.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.212.down_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.213.gate_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.213.up_proj.weight": "model-00055-of-000163.safetensors", + "model.layers.22.mlp.experts.213.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.214.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.214.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.214.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.215.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.215.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.215.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.216.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.216.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.216.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.217.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.217.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.217.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.218.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.218.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.218.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.219.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.219.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.219.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.220.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.220.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.220.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.221.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.221.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.221.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.222.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.222.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.222.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.223.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.223.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.223.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.224.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.224.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.224.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.225.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.225.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.225.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.226.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.226.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.226.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.227.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.227.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.227.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.228.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.228.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.228.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.229.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.229.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.229.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.230.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.230.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.230.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.231.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.231.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.231.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.232.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.232.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.232.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.233.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.233.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.233.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.234.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.234.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.234.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.235.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.235.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.235.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.236.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.236.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.236.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.237.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.237.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.237.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.238.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.238.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.238.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.239.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.239.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.239.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.240.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.240.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.240.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.241.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.241.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.241.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.242.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.242.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.242.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.243.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.243.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.243.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.244.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.244.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.244.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.245.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.245.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.245.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.246.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.246.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.246.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.247.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.247.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.247.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.248.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.248.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.248.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.249.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.249.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.249.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.250.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.250.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.250.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.251.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.251.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.251.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.252.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.252.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.252.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.253.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.253.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.253.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.254.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.254.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.254.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.255.gate_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.255.up_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.mlp.experts.255.down_proj.weight": "model-00056-of-000163.safetensors", + "model.layers.22.input_layernorm.weight": "model-00056-of-000163.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00056-of-000163.safetensors", + "model.layers.23.self_attn.q_a_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.q_a_layernorm.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.q_b_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.kv_b_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.indexer.wq_b.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.indexer.wk.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.indexer.k_norm.weight": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.indexer.k_norm.bias": "model-00057-of-000163.safetensors", + "model.layers.23.self_attn.indexer.weights_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.gate.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00057-of-000163.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.128.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.128.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.128.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.129.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.129.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.129.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.130.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.130.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.130.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.131.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.131.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.131.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.132.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.132.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.132.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.133.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.133.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.133.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.134.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.134.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.134.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.135.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.135.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.135.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.136.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.136.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.136.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.137.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.137.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.137.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.138.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.138.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.138.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.139.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.139.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.139.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.140.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.140.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.140.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.141.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.141.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.141.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.142.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.142.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.142.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.143.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.143.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.143.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.144.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.144.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.144.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.145.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.145.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.145.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.146.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.146.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.146.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.147.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.147.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.147.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.148.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.148.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.148.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.149.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.149.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.149.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.150.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.150.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.150.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.151.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.151.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.151.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.152.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.152.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.152.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.153.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.153.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.153.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.154.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.154.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.154.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.155.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.155.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.155.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.156.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.156.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.156.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.157.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.157.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.157.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.158.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.158.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.158.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.159.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.159.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.159.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.160.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.160.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.160.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.161.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.161.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.161.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.162.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.162.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.162.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.163.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.163.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.163.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.164.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.164.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.164.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.165.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.165.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.165.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.166.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.166.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.166.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.167.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.167.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.167.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.168.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.168.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.168.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.169.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.169.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.169.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.170.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.170.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.170.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.171.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.171.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.171.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.172.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.172.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.172.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.173.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.173.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.173.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.174.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.174.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.174.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.175.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.175.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.175.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.176.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.176.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.176.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.177.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.177.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.177.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.178.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.178.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.178.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.179.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.179.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.179.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.180.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.180.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.180.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.181.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.181.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.181.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.182.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.182.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.182.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.183.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.183.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.183.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.184.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.184.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.184.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.185.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.185.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.185.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.186.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.186.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.186.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.187.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.187.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.187.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.188.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.188.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.188.down_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.189.gate_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.189.up_proj.weight": "model-00058-of-000163.safetensors", + "model.layers.23.mlp.experts.189.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.190.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.190.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.190.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.191.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.191.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.191.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.192.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.192.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.192.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.193.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.193.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.193.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.194.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.194.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.194.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.195.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.195.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.195.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.196.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.196.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.196.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.197.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.197.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.197.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.198.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.198.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.198.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.199.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.199.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.199.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.200.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.200.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.200.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.201.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.201.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.201.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.202.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.202.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.202.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.203.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.203.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.203.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.204.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.204.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.204.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.205.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.205.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.205.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.206.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.206.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.206.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.207.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.207.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.207.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.208.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.208.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.208.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.209.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.209.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.209.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.210.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.210.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.210.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.211.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.211.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.211.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.212.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.212.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.212.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.213.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.213.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.213.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.214.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.214.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.214.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.215.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.215.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.215.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.216.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.216.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.216.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.217.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.217.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.217.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.218.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.218.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.218.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.219.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.219.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.219.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.220.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.220.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.220.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.221.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.221.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.221.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.222.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.222.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.222.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.223.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.223.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.223.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.224.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.224.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.224.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.225.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.225.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.225.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.226.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.226.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.226.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.227.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.227.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.227.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.228.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.228.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.228.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.229.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.229.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.229.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.230.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.230.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.230.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.231.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.231.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.231.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.232.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.232.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.232.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.233.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.233.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.233.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.234.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.234.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.234.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.235.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.235.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.235.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.236.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.236.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.236.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.237.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.237.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.237.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.238.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.238.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.238.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.239.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.239.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.239.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.240.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.240.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.240.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.241.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.241.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.241.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.242.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.242.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.242.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.243.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.243.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.243.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.244.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.244.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.244.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.245.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.245.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.245.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.246.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.246.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.246.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.247.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.247.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.247.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.248.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.248.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.248.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.249.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.249.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.249.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.250.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.250.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.250.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.251.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.251.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.251.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.252.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.252.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.252.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.253.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.253.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.253.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.254.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.254.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.254.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.255.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.255.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.mlp.experts.255.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.23.input_layernorm.weight": "model-00059-of-000163.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.q_a_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.q_a_layernorm.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.q_b_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.kv_b_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.indexer.wq_b.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.indexer.wk.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.indexer.k_norm.weight": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.indexer.k_norm.bias": "model-00059-of-000163.safetensors", + "model.layers.24.self_attn.indexer.weights_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.gate.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00059-of-000163.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00060-of-000163.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.128.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.128.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.128.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.129.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.129.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.129.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.130.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.130.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.130.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.131.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.131.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.131.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.132.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.132.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.132.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.133.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.133.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.133.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.134.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.134.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.134.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.135.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.135.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.135.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.136.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.136.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.136.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.137.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.137.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.137.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.138.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.138.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.138.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.139.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.139.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.139.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.140.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.140.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.140.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.141.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.141.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.141.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.142.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.142.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.142.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.143.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.143.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.143.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.144.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.144.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.144.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.145.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.145.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.145.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.146.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.146.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.146.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.147.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.147.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.147.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.148.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.148.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.148.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.149.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.149.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.149.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.150.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.150.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.150.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.151.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.151.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.151.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.152.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.152.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.152.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.153.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.153.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.153.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.154.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.154.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.154.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.155.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.155.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.155.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.156.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.156.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.156.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.157.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.157.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.157.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.158.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.158.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.158.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.159.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.159.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.159.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.160.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.160.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.160.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.161.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.161.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.161.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.162.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.162.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.162.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.163.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.163.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.163.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.164.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.164.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.164.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.165.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.165.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.165.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.166.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.166.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.166.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.167.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.167.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.167.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.168.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.168.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.168.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.169.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.169.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.169.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.170.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.170.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.170.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.171.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.171.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.171.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.172.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.172.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.172.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.173.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.173.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.173.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.174.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.174.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.174.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.175.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.175.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.175.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.176.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.176.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.176.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.177.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.177.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.177.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.178.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.178.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.178.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.179.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.179.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.179.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.180.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.180.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.180.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.181.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.181.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.181.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.182.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.182.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.182.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.183.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.183.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.183.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.184.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.184.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.184.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.185.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.185.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.185.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.186.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.186.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.186.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.187.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.187.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.187.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.188.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.188.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.188.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.189.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.189.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.189.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.190.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.190.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.190.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.191.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.191.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.191.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.192.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.192.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.192.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.193.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.193.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.193.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.194.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.194.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.194.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.195.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.195.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.195.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.196.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.196.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.196.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.197.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.197.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.197.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.198.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.198.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.198.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.199.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.199.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.199.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.200.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.200.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.200.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.201.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.201.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.201.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.202.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.202.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.202.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.203.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.203.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.203.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.204.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.204.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.204.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.205.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.205.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.205.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.206.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.206.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.206.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.207.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.207.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.207.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.208.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.208.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.208.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.209.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.209.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.209.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.210.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.210.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.210.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.211.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.211.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.211.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.212.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.212.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.212.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.213.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.213.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.213.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.214.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.214.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.214.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.215.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.215.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.215.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.216.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.216.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.216.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.217.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.217.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.217.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.218.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.218.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.218.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.219.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.219.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.219.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.220.gate_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.220.up_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.220.down_proj.weight": "model-00061-of-000163.safetensors", + "model.layers.24.mlp.experts.221.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.221.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.221.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.222.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.222.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.222.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.223.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.223.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.223.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.224.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.224.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.224.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.225.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.225.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.225.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.226.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.226.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.226.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.227.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.227.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.227.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.228.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.228.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.228.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.229.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.229.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.229.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.230.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.230.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.230.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.231.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.231.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.231.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.232.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.232.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.232.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.233.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.233.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.233.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.234.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.234.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.234.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.235.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.235.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.235.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.236.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.236.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.236.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.237.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.237.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.237.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.238.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.238.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.238.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.239.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.239.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.239.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.240.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.240.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.240.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.241.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.241.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.241.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.242.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.242.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.242.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.243.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.243.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.243.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.244.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.244.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.244.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.245.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.245.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.245.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.246.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.246.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.246.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.247.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.247.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.247.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.248.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.248.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.248.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.249.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.249.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.249.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.250.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.250.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.250.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.251.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.251.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.251.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.252.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.252.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.252.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.253.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.253.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.253.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.254.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.254.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.254.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.255.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.255.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.mlp.experts.255.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.24.input_layernorm.weight": "model-00062-of-000163.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.q_a_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.q_a_layernorm.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.q_b_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.kv_b_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.indexer.wq_b.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.indexer.wk.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.indexer.k_norm.weight": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.indexer.k_norm.bias": "model-00062-of-000163.safetensors", + "model.layers.25.self_attn.indexer.weights_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.gate.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00062-of-000163.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.128.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.128.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.128.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.129.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.129.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.129.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.130.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.130.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.130.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.131.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.131.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.131.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.132.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.132.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.132.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.133.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.133.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.133.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.134.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.134.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.134.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.135.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.135.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.135.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.136.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.136.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.136.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.137.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.137.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.137.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.138.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.138.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.138.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.139.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.139.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.139.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.140.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.140.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.140.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.141.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.141.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.141.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.142.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.142.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.142.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.143.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.143.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.143.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.144.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.144.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.144.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.145.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.145.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.145.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.146.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.146.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.146.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.147.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.147.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.147.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.148.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.148.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.148.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.149.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.149.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.149.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.150.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.150.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.150.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.151.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.151.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.151.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.152.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.152.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.152.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.153.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.153.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.153.down_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.154.gate_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.154.up_proj.weight": "model-00063-of-000163.safetensors", + "model.layers.25.mlp.experts.154.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.155.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.155.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.155.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.156.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.156.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.156.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.157.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.157.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.157.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.158.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.158.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.158.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.159.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.159.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.159.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.160.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.160.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.160.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.161.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.161.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.161.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.162.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.162.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.162.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.163.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.163.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.163.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.164.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.164.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.164.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.165.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.165.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.165.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.166.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.166.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.166.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.167.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.167.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.167.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.168.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.168.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.168.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.169.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.169.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.169.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.170.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.170.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.170.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.171.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.171.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.171.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.172.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.172.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.172.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.173.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.173.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.173.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.174.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.174.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.174.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.175.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.175.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.175.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.176.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.176.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.176.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.177.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.177.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.177.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.178.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.178.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.178.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.179.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.179.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.179.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.180.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.180.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.180.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.181.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.181.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.181.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.182.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.182.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.182.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.183.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.183.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.183.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.184.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.184.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.184.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.185.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.185.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.185.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.186.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.186.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.186.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.187.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.187.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.187.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.188.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.188.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.188.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.189.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.189.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.189.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.190.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.190.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.190.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.191.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.191.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.191.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.192.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.192.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.192.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.193.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.193.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.193.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.194.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.194.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.194.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.195.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.195.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.195.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.196.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.196.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.196.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.197.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.197.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.197.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.198.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.198.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.198.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.199.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.199.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.199.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.200.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.200.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.200.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.201.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.201.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.201.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.202.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.202.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.202.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.203.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.203.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.203.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.204.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.204.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.204.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.205.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.205.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.205.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.206.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.206.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.206.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.207.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.207.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.207.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.208.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.208.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.208.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.209.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.209.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.209.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.210.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.210.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.210.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.211.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.211.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.211.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.212.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.212.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.212.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.213.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.213.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.213.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.214.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.214.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.214.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.215.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.215.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.215.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.216.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.216.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.216.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.217.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.217.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.217.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.218.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.218.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.218.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.219.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.219.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.219.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.220.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.220.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.220.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.221.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.221.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.221.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.222.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.222.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.222.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.223.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.223.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.223.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.224.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.224.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.224.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.225.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.225.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.225.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.226.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.226.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.226.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.227.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.227.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.227.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.228.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.228.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.228.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.229.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.229.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.229.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.230.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.230.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.230.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.231.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.231.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.231.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.232.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.232.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.232.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.233.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.233.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.233.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.234.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.234.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.234.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.235.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.235.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.235.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.236.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.236.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.236.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.237.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.237.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.237.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.238.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.238.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.238.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.239.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.239.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.239.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.240.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.240.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.240.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.241.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.241.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.241.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.242.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.242.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.242.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.243.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.243.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.243.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.244.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.244.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.244.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.245.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.245.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.245.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.246.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.246.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.246.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.247.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.247.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.247.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.248.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.248.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.248.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.249.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.249.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.249.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.250.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.250.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.250.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.251.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.251.up_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.251.down_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.252.gate_proj.weight": "model-00064-of-000163.safetensors", + "model.layers.25.mlp.experts.252.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.252.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.253.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.253.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.253.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.254.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.254.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.254.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.255.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.255.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.mlp.experts.255.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.25.input_layernorm.weight": "model-00065-of-000163.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.q_a_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.q_a_layernorm.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.q_b_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.kv_b_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.indexer.wq_b.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.indexer.wk.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.indexer.k_norm.weight": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.indexer.k_norm.bias": "model-00065-of-000163.safetensors", + "model.layers.26.self_attn.indexer.weights_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.gate.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00065-of-000163.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.128.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.128.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.128.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.129.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.129.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.129.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.130.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.130.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.130.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.131.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.131.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.131.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.132.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.132.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.132.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.133.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.133.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.133.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.134.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.134.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.134.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.135.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.135.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.135.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.136.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.136.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.136.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.137.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.137.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.137.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.138.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.138.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.138.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.139.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.139.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.139.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.140.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.140.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.140.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.141.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.141.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.141.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.142.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.142.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.142.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.143.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.143.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.143.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.144.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.144.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.144.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.145.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.145.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.145.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.146.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.146.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.146.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.147.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.147.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.147.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.148.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.148.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.148.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.149.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.149.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.149.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.150.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.150.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.150.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.151.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.151.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.151.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.152.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.152.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.152.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.153.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.153.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.153.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.154.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.154.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.154.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.155.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.155.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.155.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.156.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.156.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.156.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.157.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.157.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.157.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.158.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.158.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.158.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.159.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.159.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.159.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.160.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.160.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.160.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.161.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.161.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.161.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.162.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.162.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.162.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.163.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.163.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.163.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.164.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.164.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.164.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.165.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.165.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.165.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.166.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.166.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.166.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.167.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.167.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.167.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.168.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.168.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.168.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.169.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.169.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.169.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.170.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.170.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.170.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.171.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.171.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.171.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.172.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.172.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.172.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.173.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.173.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.173.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.174.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.174.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.174.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.175.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.175.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.175.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.176.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.176.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.176.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.177.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.177.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.177.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.178.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.178.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.178.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.179.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.179.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.179.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.180.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.180.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.180.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.181.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.181.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.181.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.182.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.182.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.182.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.183.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.183.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.183.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.184.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.184.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.184.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.185.gate_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.185.up_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.185.down_proj.weight": "model-00066-of-000163.safetensors", + "model.layers.26.mlp.experts.186.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.186.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.186.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.187.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.187.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.187.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.188.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.188.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.188.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.189.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.189.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.189.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.190.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.190.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.190.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.191.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.191.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.191.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.192.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.192.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.192.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.193.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.193.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.193.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.194.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.194.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.194.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.195.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.195.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.195.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.196.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.196.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.196.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.197.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.197.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.197.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.198.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.198.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.198.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.199.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.199.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.199.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.200.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.200.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.200.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.201.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.201.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.201.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.202.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.202.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.202.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.203.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.203.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.203.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.204.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.204.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.204.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.205.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.205.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.205.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.206.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.206.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.206.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.207.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.207.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.207.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.208.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.208.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.208.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.209.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.209.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.209.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.210.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.210.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.210.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.211.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.211.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.211.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.212.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.212.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.212.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.213.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.213.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.213.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.214.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.214.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.214.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.215.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.215.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.215.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.216.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.216.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.216.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.217.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.217.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.217.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.218.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.218.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.218.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.219.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.219.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.219.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.220.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.220.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.220.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.221.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.221.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.221.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.222.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.222.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.222.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.223.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.223.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.223.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.224.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.224.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.224.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.225.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.225.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.225.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.226.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.226.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.226.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.227.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.227.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.227.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.228.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.228.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.228.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.229.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.229.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.229.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.230.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.230.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.230.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.231.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.231.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.231.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.232.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.232.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.232.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.233.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.233.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.233.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.234.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.234.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.234.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.235.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.235.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.235.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.236.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.236.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.236.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.237.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.237.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.237.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.238.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.238.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.238.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.239.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.239.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.239.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.240.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.240.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.240.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.241.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.241.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.241.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.242.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.242.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.242.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.243.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.243.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.243.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.244.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.244.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.244.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.245.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.245.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.245.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.246.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.246.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.246.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.247.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.247.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.247.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.248.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.248.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.248.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.249.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.249.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.249.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.250.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.250.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.250.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.251.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.251.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.251.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.252.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.252.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.252.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.253.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.253.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.253.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.254.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.254.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.254.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.255.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.255.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.mlp.experts.255.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.26.input_layernorm.weight": "model-00067-of-000163.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.q_a_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.q_a_layernorm.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.q_b_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.kv_b_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.indexer.wq_b.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.indexer.wk.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.indexer.k_norm.weight": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.indexer.k_norm.bias": "model-00067-of-000163.safetensors", + "model.layers.27.self_attn.indexer.weights_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.gate.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00067-of-000163.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00068-of-000163.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.128.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.128.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.128.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.129.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.129.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.129.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.130.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.130.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.130.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.131.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.131.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.131.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.132.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.132.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.132.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.133.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.133.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.133.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.134.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.134.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.134.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.135.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.135.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.135.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.136.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.136.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.136.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.137.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.137.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.137.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.138.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.138.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.138.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.139.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.139.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.139.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.140.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.140.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.140.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.141.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.141.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.141.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.142.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.142.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.142.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.143.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.143.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.143.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.144.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.144.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.144.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.145.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.145.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.145.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.146.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.146.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.146.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.147.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.147.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.147.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.148.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.148.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.148.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.149.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.149.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.149.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.150.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.150.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.150.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.151.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.151.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.151.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.152.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.152.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.152.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.153.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.153.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.153.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.154.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.154.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.154.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.155.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.155.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.155.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.156.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.156.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.156.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.157.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.157.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.157.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.158.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.158.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.158.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.159.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.159.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.159.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.160.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.160.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.160.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.161.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.161.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.161.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.162.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.162.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.162.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.163.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.163.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.163.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.164.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.164.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.164.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.165.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.165.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.165.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.166.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.166.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.166.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.167.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.167.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.167.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.168.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.168.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.168.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.169.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.169.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.169.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.170.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.170.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.170.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.171.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.171.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.171.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.172.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.172.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.172.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.173.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.173.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.173.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.174.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.174.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.174.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.175.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.175.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.175.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.176.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.176.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.176.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.177.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.177.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.177.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.178.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.178.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.178.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.179.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.179.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.179.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.180.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.180.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.180.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.181.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.181.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.181.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.182.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.182.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.182.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.183.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.183.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.183.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.184.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.184.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.184.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.185.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.185.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.185.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.186.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.186.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.186.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.187.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.187.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.187.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.188.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.188.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.188.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.189.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.189.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.189.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.190.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.190.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.190.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.191.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.191.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.191.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.192.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.192.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.192.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.193.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.193.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.193.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.194.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.194.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.194.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.195.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.195.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.195.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.196.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.196.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.196.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.197.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.197.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.197.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.198.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.198.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.198.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.199.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.199.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.199.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.200.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.200.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.200.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.201.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.201.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.201.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.202.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.202.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.202.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.203.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.203.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.203.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.204.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.204.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.204.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.205.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.205.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.205.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.206.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.206.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.206.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.207.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.207.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.207.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.208.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.208.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.208.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.209.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.209.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.209.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.210.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.210.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.210.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.211.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.211.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.211.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.212.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.212.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.212.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.213.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.213.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.213.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.214.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.214.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.214.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.215.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.215.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.215.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.216.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.216.up_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.216.down_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.217.gate_proj.weight": "model-00069-of-000163.safetensors", + "model.layers.27.mlp.experts.217.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.217.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.218.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.218.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.218.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.219.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.219.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.219.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.220.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.220.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.220.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.221.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.221.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.221.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.222.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.222.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.222.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.223.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.223.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.223.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.224.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.224.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.224.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.225.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.225.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.225.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.226.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.226.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.226.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.227.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.227.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.227.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.228.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.228.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.228.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.229.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.229.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.229.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.230.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.230.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.230.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.231.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.231.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.231.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.232.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.232.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.232.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.233.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.233.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.233.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.234.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.234.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.234.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.235.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.235.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.235.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.236.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.236.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.236.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.237.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.237.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.237.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.238.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.238.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.238.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.239.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.239.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.239.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.240.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.240.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.240.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.241.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.241.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.241.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.242.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.242.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.242.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.243.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.243.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.243.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.244.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.244.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.244.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.245.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.245.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.245.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.246.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.246.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.246.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.247.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.247.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.247.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.248.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.248.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.248.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.249.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.249.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.249.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.250.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.250.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.250.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.251.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.251.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.251.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.252.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.252.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.252.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.253.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.253.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.253.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.254.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.254.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.254.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.255.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.255.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.mlp.experts.255.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.27.input_layernorm.weight": "model-00070-of-000163.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.q_a_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.q_a_layernorm.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.q_b_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.kv_b_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.indexer.wq_b.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.indexer.wk.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.indexer.k_norm.weight": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.indexer.k_norm.bias": "model-00070-of-000163.safetensors", + "model.layers.28.self_attn.indexer.weights_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.gate.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00070-of-000163.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.128.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.128.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.128.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.129.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.129.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.129.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.130.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.130.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.130.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.131.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.131.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.131.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.132.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.132.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.132.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.133.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.133.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.133.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.134.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.134.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.134.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.135.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.135.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.135.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.136.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.136.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.136.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.137.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.137.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.137.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.138.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.138.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.138.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.139.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.139.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.139.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.140.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.140.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.140.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.141.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.141.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.141.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.142.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.142.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.142.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.143.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.143.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.143.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.144.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.144.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.144.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.145.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.145.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.145.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.146.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.146.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.146.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.147.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.147.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.147.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.148.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.148.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.148.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.149.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.149.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.149.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.150.gate_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.150.up_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.150.down_proj.weight": "model-00071-of-000163.safetensors", + "model.layers.28.mlp.experts.151.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.151.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.151.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.152.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.152.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.152.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.153.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.153.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.153.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.154.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.154.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.154.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.155.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.155.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.155.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.156.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.156.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.156.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.157.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.157.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.157.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.158.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.158.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.158.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.159.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.159.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.159.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.160.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.160.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.160.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.161.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.161.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.161.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.162.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.162.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.162.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.163.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.163.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.163.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.164.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.164.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.164.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.165.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.165.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.165.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.166.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.166.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.166.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.167.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.167.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.167.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.168.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.168.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.168.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.169.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.169.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.169.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.170.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.170.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.170.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.171.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.171.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.171.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.172.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.172.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.172.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.173.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.173.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.173.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.174.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.174.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.174.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.175.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.175.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.175.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.176.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.176.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.176.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.177.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.177.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.177.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.178.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.178.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.178.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.179.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.179.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.179.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.180.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.180.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.180.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.181.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.181.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.181.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.182.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.182.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.182.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.183.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.183.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.183.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.184.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.184.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.184.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.185.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.185.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.185.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.186.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.186.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.186.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.187.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.187.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.187.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.188.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.188.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.188.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.189.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.189.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.189.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.190.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.190.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.190.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.191.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.191.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.191.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.192.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.192.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.192.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.193.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.193.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.193.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.194.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.194.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.194.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.195.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.195.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.195.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.196.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.196.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.196.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.197.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.197.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.197.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.198.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.198.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.198.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.199.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.199.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.199.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.200.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.200.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.200.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.201.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.201.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.201.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.202.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.202.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.202.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.203.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.203.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.203.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.204.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.204.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.204.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.205.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.205.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.205.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.206.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.206.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.206.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.207.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.207.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.207.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.208.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.208.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.208.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.209.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.209.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.209.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.210.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.210.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.210.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.211.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.211.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.211.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.212.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.212.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.212.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.213.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.213.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.213.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.214.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.214.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.214.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.215.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.215.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.215.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.216.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.216.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.216.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.217.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.217.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.217.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.218.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.218.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.218.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.219.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.219.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.219.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.220.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.220.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.220.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.221.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.221.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.221.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.222.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.222.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.222.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.223.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.223.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.223.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.224.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.224.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.224.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.225.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.225.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.225.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.226.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.226.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.226.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.227.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.227.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.227.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.228.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.228.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.228.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.229.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.229.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.229.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.230.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.230.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.230.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.231.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.231.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.231.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.232.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.232.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.232.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.233.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.233.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.233.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.234.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.234.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.234.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.235.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.235.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.235.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.236.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.236.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.236.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.237.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.237.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.237.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.238.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.238.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.238.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.239.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.239.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.239.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.240.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.240.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.240.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.241.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.241.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.241.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.242.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.242.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.242.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.243.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.243.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.243.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.244.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.244.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.244.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.245.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.245.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.245.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.246.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.246.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.246.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.247.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.247.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.247.down_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.248.gate_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.248.up_proj.weight": "model-00072-of-000163.safetensors", + "model.layers.28.mlp.experts.248.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.249.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.249.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.249.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.250.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.250.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.250.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.251.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.251.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.251.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.252.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.252.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.252.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.253.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.253.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.253.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.254.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.254.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.254.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.255.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.255.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.mlp.experts.255.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.28.input_layernorm.weight": "model-00073-of-000163.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.q_a_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.q_a_layernorm.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.q_b_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.kv_b_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.indexer.wq_b.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.indexer.wk.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.indexer.k_norm.weight": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.indexer.k_norm.bias": "model-00073-of-000163.safetensors", + "model.layers.29.self_attn.indexer.weights_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.gate.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00073-of-000163.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.128.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.128.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.128.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.129.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.129.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.129.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.130.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.130.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.130.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.131.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.131.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.131.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.132.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.132.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.132.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.133.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.133.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.133.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.134.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.134.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.134.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.135.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.135.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.135.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.136.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.136.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.136.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.137.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.137.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.137.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.138.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.138.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.138.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.139.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.139.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.139.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.140.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.140.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.140.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.141.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.141.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.141.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.142.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.142.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.142.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.143.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.143.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.143.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.144.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.144.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.144.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.145.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.145.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.145.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.146.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.146.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.146.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.147.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.147.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.147.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.148.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.148.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.148.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.149.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.149.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.149.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.150.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.150.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.150.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.151.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.151.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.151.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.152.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.152.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.152.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.153.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.153.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.153.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.154.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.154.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.154.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.155.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.155.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.155.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.156.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.156.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.156.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.157.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.157.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.157.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.158.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.158.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.158.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.159.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.159.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.159.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.160.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.160.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.160.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.161.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.161.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.161.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.162.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.162.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.162.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.163.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.163.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.163.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.164.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.164.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.164.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.165.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.165.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.165.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.166.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.166.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.166.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.167.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.167.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.167.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.168.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.168.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.168.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.169.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.169.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.169.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.170.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.170.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.170.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.171.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.171.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.171.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.172.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.172.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.172.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.173.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.173.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.173.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.174.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.174.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.174.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.175.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.175.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.175.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.176.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.176.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.176.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.177.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.177.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.177.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.178.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.178.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.178.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.179.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.179.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.179.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.180.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.180.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.180.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.181.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.181.up_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.181.down_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.182.gate_proj.weight": "model-00074-of-000163.safetensors", + "model.layers.29.mlp.experts.182.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.182.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.183.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.183.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.183.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.184.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.184.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.184.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.185.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.185.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.185.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.186.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.186.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.186.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.187.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.187.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.187.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.188.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.188.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.188.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.189.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.189.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.189.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.190.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.190.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.190.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.191.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.191.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.191.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.192.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.192.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.192.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.193.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.193.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.193.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.194.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.194.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.194.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.195.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.195.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.195.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.196.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.196.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.196.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.197.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.197.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.197.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.198.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.198.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.198.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.199.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.199.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.199.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.200.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.200.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.200.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.201.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.201.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.201.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.202.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.202.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.202.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.203.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.203.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.203.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.204.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.204.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.204.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.205.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.205.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.205.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.206.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.206.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.206.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.207.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.207.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.207.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.208.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.208.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.208.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.209.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.209.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.209.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.210.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.210.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.210.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.211.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.211.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.211.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.212.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.212.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.212.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.213.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.213.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.213.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.214.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.214.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.214.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.215.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.215.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.215.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.216.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.216.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.216.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.217.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.217.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.217.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.218.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.218.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.218.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.219.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.219.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.219.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.220.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.220.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.220.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.221.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.221.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.221.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.222.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.222.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.222.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.223.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.223.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.223.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.224.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.224.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.224.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.225.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.225.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.225.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.226.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.226.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.226.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.227.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.227.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.227.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.228.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.228.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.228.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.229.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.229.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.229.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.230.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.230.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.230.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.231.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.231.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.231.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.232.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.232.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.232.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.233.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.233.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.233.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.234.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.234.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.234.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.235.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.235.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.235.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.236.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.236.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.236.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.237.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.237.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.237.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.238.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.238.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.238.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.239.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.239.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.239.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.240.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.240.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.240.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.241.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.241.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.241.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.242.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.242.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.242.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.243.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.243.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.243.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.244.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.244.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.244.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.245.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.245.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.245.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.246.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.246.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.246.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.247.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.247.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.247.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.248.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.248.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.248.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.249.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.249.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.249.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.250.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.250.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.250.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.251.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.251.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.251.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.252.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.252.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.252.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.253.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.253.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.253.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.254.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.254.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.254.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.255.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.255.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.mlp.experts.255.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.29.input_layernorm.weight": "model-00075-of-000163.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.q_a_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.q_a_layernorm.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.q_b_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.kv_b_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.indexer.wq_b.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.indexer.wk.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.indexer.k_norm.weight": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.indexer.k_norm.bias": "model-00075-of-000163.safetensors", + "model.layers.30.self_attn.indexer.weights_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.gate.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00075-of-000163.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00076-of-000163.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.128.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.128.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.128.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.129.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.129.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.129.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.130.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.130.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.130.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.131.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.131.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.131.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.132.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.132.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.132.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.133.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.133.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.133.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.134.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.134.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.134.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.135.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.135.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.135.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.136.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.136.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.136.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.137.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.137.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.137.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.138.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.138.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.138.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.139.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.139.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.139.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.140.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.140.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.140.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.141.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.141.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.141.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.142.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.142.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.142.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.143.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.143.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.143.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.144.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.144.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.144.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.145.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.145.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.145.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.146.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.146.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.146.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.147.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.147.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.147.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.148.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.148.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.148.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.149.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.149.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.149.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.150.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.150.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.150.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.151.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.151.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.151.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.152.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.152.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.152.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.153.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.153.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.153.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.154.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.154.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.154.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.155.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.155.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.155.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.156.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.156.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.156.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.157.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.157.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.157.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.158.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.158.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.158.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.159.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.159.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.159.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.160.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.160.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.160.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.161.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.161.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.161.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.162.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.162.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.162.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.163.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.163.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.163.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.164.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.164.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.164.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.165.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.165.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.165.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.166.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.166.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.166.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.167.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.167.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.167.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.168.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.168.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.168.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.169.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.169.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.169.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.170.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.170.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.170.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.171.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.171.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.171.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.172.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.172.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.172.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.173.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.173.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.173.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.174.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.174.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.174.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.175.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.175.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.175.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.176.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.176.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.176.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.177.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.177.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.177.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.178.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.178.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.178.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.179.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.179.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.179.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.180.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.180.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.180.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.181.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.181.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.181.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.182.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.182.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.182.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.183.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.183.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.183.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.184.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.184.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.184.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.185.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.185.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.185.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.186.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.186.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.186.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.187.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.187.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.187.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.188.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.188.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.188.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.189.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.189.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.189.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.190.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.190.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.190.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.191.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.191.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.191.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.192.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.192.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.192.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.193.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.193.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.193.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.194.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.194.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.194.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.195.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.195.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.195.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.196.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.196.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.196.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.197.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.197.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.197.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.198.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.198.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.198.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.199.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.199.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.199.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.200.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.200.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.200.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.201.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.201.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.201.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.202.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.202.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.202.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.203.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.203.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.203.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.204.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.204.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.204.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.205.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.205.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.205.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.206.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.206.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.206.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.207.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.207.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.207.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.208.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.208.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.208.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.209.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.209.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.209.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.210.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.210.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.210.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.211.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.211.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.211.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.212.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.212.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.212.down_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.213.gate_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.213.up_proj.weight": "model-00077-of-000163.safetensors", + "model.layers.30.mlp.experts.213.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.214.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.214.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.214.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.215.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.215.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.215.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.216.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.216.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.216.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.217.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.217.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.217.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.218.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.218.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.218.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.219.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.219.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.219.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.220.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.220.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.220.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.221.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.221.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.221.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.222.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.222.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.222.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.223.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.223.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.223.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.224.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.224.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.224.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.225.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.225.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.225.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.226.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.226.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.226.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.227.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.227.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.227.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.228.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.228.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.228.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.229.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.229.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.229.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.230.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.230.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.230.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.231.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.231.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.231.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.232.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.232.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.232.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.233.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.233.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.233.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.234.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.234.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.234.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.235.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.235.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.235.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.236.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.236.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.236.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.237.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.237.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.237.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.238.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.238.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.238.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.239.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.239.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.239.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.240.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.240.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.240.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.241.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.241.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.241.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.242.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.242.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.242.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.243.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.243.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.243.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.244.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.244.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.244.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.245.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.245.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.245.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.246.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.246.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.246.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.247.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.247.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.247.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.248.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.248.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.248.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.249.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.249.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.249.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.250.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.250.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.250.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.251.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.251.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.251.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.252.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.252.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.252.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.253.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.253.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.253.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.254.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.254.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.254.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.255.gate_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.255.up_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.mlp.experts.255.down_proj.weight": "model-00078-of-000163.safetensors", + "model.layers.30.input_layernorm.weight": "model-00078-of-000163.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00078-of-000163.safetensors", + "model.layers.31.self_attn.q_a_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.q_a_layernorm.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.q_b_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.kv_b_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.indexer.wq_b.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.indexer.wk.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.indexer.k_norm.weight": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.indexer.k_norm.bias": "model-00079-of-000163.safetensors", + "model.layers.31.self_attn.indexer.weights_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.gate.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00079-of-000163.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.128.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.128.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.128.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.129.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.129.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.129.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.130.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.130.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.130.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.131.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.131.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.131.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.132.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.132.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.132.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.133.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.133.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.133.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.134.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.134.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.134.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.135.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.135.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.135.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.136.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.136.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.136.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.137.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.137.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.137.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.138.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.138.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.138.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.139.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.139.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.139.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.140.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.140.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.140.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.141.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.141.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.141.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.142.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.142.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.142.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.143.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.143.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.143.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.144.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.144.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.144.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.145.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.145.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.145.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.146.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.146.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.146.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.147.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.147.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.147.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.148.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.148.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.148.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.149.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.149.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.149.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.150.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.150.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.150.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.151.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.151.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.151.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.152.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.152.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.152.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.153.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.153.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.153.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.154.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.154.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.154.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.155.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.155.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.155.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.156.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.156.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.156.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.157.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.157.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.157.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.158.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.158.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.158.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.159.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.159.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.159.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.160.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.160.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.160.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.161.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.161.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.161.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.162.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.162.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.162.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.163.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.163.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.163.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.164.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.164.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.164.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.165.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.165.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.165.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.166.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.166.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.166.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.167.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.167.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.167.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.168.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.168.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.168.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.169.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.169.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.169.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.170.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.170.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.170.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.171.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.171.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.171.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.172.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.172.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.172.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.173.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.173.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.173.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.174.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.174.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.174.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.175.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.175.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.175.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.176.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.176.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.176.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.177.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.177.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.177.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.178.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.178.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.178.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.179.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.179.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.179.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.180.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.180.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.180.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.181.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.181.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.181.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.182.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.182.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.182.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.183.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.183.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.183.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.184.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.184.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.184.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.185.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.185.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.185.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.186.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.186.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.186.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.187.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.187.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.187.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.188.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.188.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.188.down_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.189.gate_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.189.up_proj.weight": "model-00080-of-000163.safetensors", + "model.layers.31.mlp.experts.189.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.190.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.190.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.190.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.191.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.191.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.191.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.192.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.192.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.192.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.193.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.193.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.193.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.194.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.194.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.194.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.195.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.195.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.195.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.196.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.196.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.196.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.197.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.197.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.197.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.198.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.198.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.198.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.199.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.199.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.199.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.200.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.200.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.200.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.201.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.201.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.201.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.202.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.202.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.202.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.203.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.203.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.203.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.204.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.204.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.204.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.205.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.205.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.205.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.206.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.206.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.206.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.207.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.207.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.207.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.208.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.208.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.208.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.209.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.209.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.209.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.210.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.210.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.210.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.211.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.211.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.211.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.212.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.212.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.212.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.213.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.213.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.213.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.214.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.214.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.214.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.215.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.215.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.215.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.216.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.216.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.216.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.217.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.217.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.217.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.218.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.218.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.218.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.219.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.219.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.219.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.220.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.220.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.220.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.221.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.221.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.221.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.222.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.222.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.222.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.223.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.223.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.223.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.224.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.224.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.224.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.225.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.225.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.225.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.226.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.226.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.226.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.227.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.227.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.227.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.228.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.228.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.228.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.229.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.229.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.229.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.230.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.230.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.230.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.231.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.231.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.231.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.232.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.232.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.232.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.233.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.233.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.233.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.234.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.234.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.234.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.235.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.235.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.235.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.236.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.236.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.236.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.237.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.237.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.237.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.238.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.238.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.238.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.239.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.239.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.239.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.240.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.240.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.240.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.241.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.241.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.241.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.242.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.242.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.242.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.243.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.243.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.243.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.244.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.244.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.244.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.245.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.245.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.245.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.246.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.246.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.246.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.247.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.247.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.247.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.248.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.248.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.248.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.249.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.249.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.249.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.250.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.250.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.250.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.251.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.251.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.251.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.252.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.252.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.252.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.253.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.253.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.253.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.254.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.254.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.254.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.255.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.255.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.mlp.experts.255.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.31.input_layernorm.weight": "model-00081-of-000163.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.q_a_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.q_a_layernorm.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.q_b_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.kv_b_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.indexer.wq_b.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.indexer.wk.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.indexer.k_norm.weight": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.indexer.k_norm.bias": "model-00081-of-000163.safetensors", + "model.layers.32.self_attn.indexer.weights_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.gate.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00081-of-000163.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00082-of-000163.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.128.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.128.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.128.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.129.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.129.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.129.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.130.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.130.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.130.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.131.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.131.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.131.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.132.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.132.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.132.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.133.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.133.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.133.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.134.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.134.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.134.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.135.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.135.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.135.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.136.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.136.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.136.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.137.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.137.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.137.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.138.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.138.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.138.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.139.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.139.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.139.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.140.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.140.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.140.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.141.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.141.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.141.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.142.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.142.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.142.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.143.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.143.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.143.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.144.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.144.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.144.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.145.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.145.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.145.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.146.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.146.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.146.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.147.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.147.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.147.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.148.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.148.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.148.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.149.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.149.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.149.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.150.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.150.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.150.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.151.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.151.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.151.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.152.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.152.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.152.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.153.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.153.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.153.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.154.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.154.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.154.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.155.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.155.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.155.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.156.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.156.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.156.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.157.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.157.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.157.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.158.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.158.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.158.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.159.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.159.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.159.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.160.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.160.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.160.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.161.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.161.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.161.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.162.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.162.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.162.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.163.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.163.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.163.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.164.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.164.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.164.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.165.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.165.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.165.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.166.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.166.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.166.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.167.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.167.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.167.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.168.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.168.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.168.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.169.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.169.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.169.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.170.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.170.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.170.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.171.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.171.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.171.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.172.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.172.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.172.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.173.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.173.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.173.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.174.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.174.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.174.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.175.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.175.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.175.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.176.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.176.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.176.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.177.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.177.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.177.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.178.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.178.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.178.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.179.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.179.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.179.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.180.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.180.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.180.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.181.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.181.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.181.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.182.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.182.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.182.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.183.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.183.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.183.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.184.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.184.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.184.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.185.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.185.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.185.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.186.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.186.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.186.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.187.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.187.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.187.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.188.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.188.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.188.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.189.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.189.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.189.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.190.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.190.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.190.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.191.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.191.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.191.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.192.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.192.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.192.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.193.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.193.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.193.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.194.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.194.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.194.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.195.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.195.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.195.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.196.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.196.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.196.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.197.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.197.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.197.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.198.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.198.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.198.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.199.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.199.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.199.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.200.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.200.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.200.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.201.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.201.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.201.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.202.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.202.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.202.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.203.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.203.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.203.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.204.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.204.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.204.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.205.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.205.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.205.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.206.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.206.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.206.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.207.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.207.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.207.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.208.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.208.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.208.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.209.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.209.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.209.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.210.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.210.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.210.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.211.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.211.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.211.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.212.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.212.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.212.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.213.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.213.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.213.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.214.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.214.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.214.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.215.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.215.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.215.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.216.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.216.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.216.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.217.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.217.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.217.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.218.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.218.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.218.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.219.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.219.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.219.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.220.gate_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.220.up_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.220.down_proj.weight": "model-00083-of-000163.safetensors", + "model.layers.32.mlp.experts.221.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.221.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.221.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.222.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.222.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.222.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.223.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.223.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.223.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.224.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.224.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.224.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.225.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.225.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.225.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.226.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.226.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.226.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.227.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.227.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.227.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.228.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.228.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.228.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.229.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.229.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.229.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.230.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.230.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.230.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.231.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.231.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.231.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.232.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.232.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.232.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.233.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.233.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.233.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.234.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.234.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.234.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.235.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.235.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.235.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.236.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.236.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.236.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.237.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.237.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.237.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.238.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.238.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.238.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.239.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.239.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.239.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.240.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.240.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.240.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.241.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.241.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.241.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.242.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.242.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.242.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.243.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.243.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.243.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.244.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.244.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.244.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.245.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.245.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.245.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.246.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.246.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.246.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.247.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.247.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.247.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.248.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.248.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.248.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.249.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.249.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.249.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.250.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.250.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.250.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.251.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.251.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.251.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.252.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.252.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.252.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.253.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.253.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.253.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.254.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.254.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.254.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.255.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.255.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.mlp.experts.255.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.32.input_layernorm.weight": "model-00084-of-000163.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.q_a_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.q_a_layernorm.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.q_b_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.kv_b_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.indexer.wq_b.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.indexer.wk.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.indexer.k_norm.weight": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.indexer.k_norm.bias": "model-00084-of-000163.safetensors", + "model.layers.33.self_attn.indexer.weights_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.gate.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00084-of-000163.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.128.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.128.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.128.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.129.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.129.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.129.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.130.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.130.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.130.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.131.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.131.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.131.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.132.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.132.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.132.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.133.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.133.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.133.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.134.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.134.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.134.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.135.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.135.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.135.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.136.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.136.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.136.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.137.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.137.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.137.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.138.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.138.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.138.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.139.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.139.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.139.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.140.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.140.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.140.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.141.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.141.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.141.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.142.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.142.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.142.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.143.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.143.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.143.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.144.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.144.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.144.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.145.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.145.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.145.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.146.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.146.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.146.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.147.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.147.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.147.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.148.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.148.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.148.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.149.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.149.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.149.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.150.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.150.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.150.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.151.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.151.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.151.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.152.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.152.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.152.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.153.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.153.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.153.down_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.154.gate_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.154.up_proj.weight": "model-00085-of-000163.safetensors", + "model.layers.33.mlp.experts.154.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.155.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.155.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.155.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.156.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.156.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.156.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.157.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.157.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.157.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.158.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.158.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.158.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.159.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.159.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.159.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.160.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.160.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.160.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.161.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.161.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.161.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.162.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.162.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.162.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.163.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.163.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.163.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.164.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.164.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.164.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.165.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.165.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.165.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.166.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.166.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.166.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.167.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.167.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.167.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.168.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.168.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.168.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.169.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.169.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.169.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.170.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.170.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.170.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.171.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.171.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.171.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.172.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.172.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.172.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.173.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.173.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.173.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.174.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.174.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.174.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.175.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.175.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.175.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.176.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.176.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.176.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.177.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.177.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.177.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.178.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.178.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.178.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.179.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.179.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.179.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.180.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.180.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.180.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.181.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.181.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.181.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.182.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.182.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.182.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.183.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.183.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.183.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.184.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.184.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.184.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.185.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.185.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.185.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.186.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.186.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.186.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.187.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.187.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.187.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.188.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.188.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.188.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.189.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.189.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.189.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.190.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.190.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.190.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.191.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.191.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.191.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.192.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.192.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.192.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.193.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.193.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.193.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.194.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.194.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.194.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.195.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.195.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.195.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.196.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.196.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.196.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.197.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.197.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.197.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.198.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.198.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.198.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.199.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.199.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.199.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.200.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.200.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.200.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.201.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.201.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.201.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.202.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.202.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.202.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.203.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.203.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.203.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.204.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.204.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.204.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.205.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.205.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.205.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.206.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.206.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.206.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.207.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.207.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.207.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.208.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.208.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.208.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.209.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.209.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.209.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.210.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.210.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.210.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.211.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.211.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.211.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.212.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.212.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.212.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.213.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.213.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.213.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.214.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.214.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.214.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.215.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.215.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.215.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.216.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.216.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.216.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.217.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.217.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.217.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.218.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.218.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.218.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.219.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.219.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.219.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.220.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.220.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.220.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.221.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.221.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.221.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.222.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.222.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.222.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.223.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.223.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.223.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.224.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.224.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.224.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.225.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.225.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.225.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.226.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.226.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.226.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.227.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.227.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.227.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.228.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.228.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.228.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.229.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.229.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.229.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.230.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.230.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.230.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.231.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.231.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.231.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.232.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.232.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.232.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.233.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.233.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.233.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.234.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.234.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.234.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.235.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.235.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.235.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.236.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.236.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.236.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.237.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.237.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.237.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.238.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.238.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.238.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.239.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.239.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.239.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.240.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.240.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.240.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.241.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.241.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.241.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.242.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.242.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.242.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.243.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.243.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.243.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.244.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.244.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.244.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.245.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.245.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.245.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.246.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.246.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.246.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.247.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.247.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.247.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.248.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.248.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.248.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.249.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.249.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.249.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.250.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.250.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.250.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.251.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.251.up_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.251.down_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.252.gate_proj.weight": "model-00086-of-000163.safetensors", + "model.layers.33.mlp.experts.252.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.252.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.253.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.253.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.253.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.254.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.254.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.254.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.255.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.255.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.mlp.experts.255.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.33.input_layernorm.weight": "model-00087-of-000163.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.q_a_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.q_a_layernorm.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.q_b_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.kv_b_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.indexer.wq_b.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.indexer.wk.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.indexer.k_norm.weight": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.indexer.k_norm.bias": "model-00087-of-000163.safetensors", + "model.layers.34.self_attn.indexer.weights_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.gate.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00087-of-000163.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.128.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.128.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.128.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.129.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.129.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.129.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.130.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.130.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.130.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.131.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.131.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.131.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.132.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.132.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.132.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.133.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.133.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.133.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.134.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.134.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.134.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.135.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.135.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.135.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.136.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.136.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.136.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.137.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.137.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.137.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.138.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.138.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.138.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.139.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.139.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.139.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.140.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.140.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.140.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.141.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.141.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.141.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.142.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.142.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.142.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.143.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.143.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.143.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.144.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.144.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.144.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.145.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.145.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.145.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.146.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.146.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.146.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.147.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.147.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.147.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.148.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.148.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.148.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.149.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.149.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.149.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.150.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.150.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.150.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.151.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.151.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.151.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.152.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.152.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.152.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.153.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.153.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.153.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.154.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.154.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.154.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.155.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.155.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.155.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.156.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.156.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.156.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.157.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.157.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.157.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.158.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.158.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.158.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.159.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.159.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.159.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.160.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.160.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.160.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.161.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.161.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.161.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.162.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.162.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.162.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.163.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.163.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.163.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.164.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.164.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.164.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.165.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.165.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.165.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.166.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.166.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.166.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.167.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.167.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.167.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.168.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.168.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.168.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.169.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.169.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.169.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.170.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.170.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.170.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.171.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.171.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.171.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.172.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.172.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.172.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.173.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.173.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.173.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.174.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.174.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.174.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.175.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.175.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.175.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.176.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.176.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.176.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.177.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.177.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.177.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.178.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.178.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.178.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.179.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.179.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.179.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.180.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.180.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.180.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.181.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.181.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.181.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.182.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.182.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.182.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.183.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.183.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.183.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.184.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.184.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.184.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.185.gate_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.185.up_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.185.down_proj.weight": "model-00088-of-000163.safetensors", + "model.layers.34.mlp.experts.186.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.186.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.186.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.187.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.187.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.187.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.188.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.188.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.188.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.189.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.189.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.189.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.190.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.190.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.190.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.191.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.191.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.191.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.192.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.192.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.192.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.193.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.193.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.193.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.194.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.194.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.194.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.195.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.195.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.195.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.196.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.196.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.196.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.197.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.197.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.197.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.198.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.198.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.198.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.199.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.199.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.199.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.200.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.200.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.200.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.201.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.201.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.201.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.202.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.202.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.202.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.203.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.203.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.203.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.204.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.204.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.204.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.205.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.205.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.205.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.206.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.206.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.206.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.207.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.207.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.207.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.208.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.208.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.208.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.209.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.209.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.209.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.210.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.210.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.210.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.211.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.211.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.211.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.212.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.212.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.212.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.213.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.213.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.213.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.214.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.214.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.214.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.215.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.215.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.215.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.216.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.216.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.216.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.217.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.217.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.217.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.218.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.218.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.218.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.219.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.219.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.219.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.220.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.220.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.220.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.221.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.221.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.221.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.222.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.222.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.222.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.223.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.223.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.223.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.224.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.224.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.224.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.225.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.225.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.225.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.226.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.226.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.226.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.227.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.227.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.227.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.228.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.228.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.228.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.229.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.229.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.229.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.230.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.230.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.230.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.231.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.231.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.231.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.232.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.232.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.232.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.233.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.233.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.233.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.234.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.234.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.234.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.235.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.235.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.235.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.236.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.236.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.236.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.237.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.237.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.237.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.238.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.238.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.238.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.239.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.239.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.239.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.240.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.240.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.240.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.241.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.241.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.241.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.242.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.242.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.242.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.243.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.243.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.243.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.244.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.244.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.244.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.245.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.245.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.245.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.246.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.246.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.246.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.247.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.247.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.247.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.248.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.248.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.248.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.249.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.249.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.249.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.250.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.250.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.250.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.251.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.251.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.251.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.252.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.252.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.252.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.253.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.253.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.253.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.254.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.254.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.254.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.255.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.255.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.mlp.experts.255.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.34.input_layernorm.weight": "model-00089-of-000163.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.q_a_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.q_a_layernorm.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.q_b_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.kv_b_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.indexer.wq_b.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.indexer.wk.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.indexer.k_norm.weight": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.indexer.k_norm.bias": "model-00089-of-000163.safetensors", + "model.layers.35.self_attn.indexer.weights_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.gate.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00089-of-000163.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00090-of-000163.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.128.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.128.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.128.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.129.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.129.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.129.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.130.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.130.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.130.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.131.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.131.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.131.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.132.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.132.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.132.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.133.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.133.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.133.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.134.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.134.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.134.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.135.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.135.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.135.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.136.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.136.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.136.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.137.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.137.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.137.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.138.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.138.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.138.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.139.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.139.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.139.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.140.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.140.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.140.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.141.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.141.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.141.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.142.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.142.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.142.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.143.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.143.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.143.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.144.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.144.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.144.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.145.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.145.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.145.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.146.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.146.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.146.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.147.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.147.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.147.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.148.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.148.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.148.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.149.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.149.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.149.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.150.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.150.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.150.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.151.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.151.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.151.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.152.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.152.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.152.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.153.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.153.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.153.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.154.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.154.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.154.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.155.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.155.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.155.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.156.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.156.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.156.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.157.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.157.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.157.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.158.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.158.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.158.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.159.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.159.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.159.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.160.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.160.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.160.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.161.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.161.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.161.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.162.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.162.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.162.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.163.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.163.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.163.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.164.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.164.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.164.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.165.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.165.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.165.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.166.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.166.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.166.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.167.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.167.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.167.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.168.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.168.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.168.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.169.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.169.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.169.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.170.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.170.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.170.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.171.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.171.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.171.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.172.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.172.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.172.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.173.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.173.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.173.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.174.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.174.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.174.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.175.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.175.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.175.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.176.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.176.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.176.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.177.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.177.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.177.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.178.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.178.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.178.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.179.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.179.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.179.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.180.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.180.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.180.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.181.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.181.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.181.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.182.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.182.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.182.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.183.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.183.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.183.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.184.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.184.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.184.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.185.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.185.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.185.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.186.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.186.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.186.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.187.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.187.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.187.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.188.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.188.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.188.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.189.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.189.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.189.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.190.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.190.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.190.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.191.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.191.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.191.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.192.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.192.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.192.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.193.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.193.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.193.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.194.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.194.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.194.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.195.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.195.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.195.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.196.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.196.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.196.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.197.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.197.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.197.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.198.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.198.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.198.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.199.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.199.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.199.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.200.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.200.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.200.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.201.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.201.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.201.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.202.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.202.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.202.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.203.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.203.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.203.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.204.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.204.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.204.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.205.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.205.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.205.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.206.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.206.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.206.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.207.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.207.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.207.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.208.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.208.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.208.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.209.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.209.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.209.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.210.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.210.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.210.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.211.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.211.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.211.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.212.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.212.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.212.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.213.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.213.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.213.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.214.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.214.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.214.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.215.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.215.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.215.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.216.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.216.up_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.216.down_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.217.gate_proj.weight": "model-00091-of-000163.safetensors", + "model.layers.35.mlp.experts.217.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.217.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.218.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.218.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.218.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.219.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.219.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.219.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.220.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.220.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.220.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.221.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.221.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.221.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.222.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.222.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.222.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.223.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.223.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.223.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.224.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.224.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.224.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.225.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.225.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.225.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.226.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.226.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.226.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.227.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.227.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.227.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.228.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.228.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.228.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.229.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.229.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.229.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.230.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.230.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.230.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.231.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.231.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.231.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.232.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.232.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.232.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.233.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.233.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.233.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.234.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.234.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.234.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.235.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.235.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.235.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.236.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.236.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.236.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.237.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.237.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.237.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.238.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.238.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.238.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.239.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.239.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.239.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.240.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.240.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.240.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.241.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.241.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.241.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.242.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.242.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.242.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.243.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.243.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.243.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.244.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.244.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.244.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.245.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.245.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.245.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.246.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.246.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.246.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.247.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.247.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.247.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.248.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.248.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.248.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.249.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.249.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.249.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.250.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.250.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.250.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.251.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.251.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.251.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.252.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.252.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.252.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.253.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.253.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.253.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.254.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.254.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.254.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.255.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.255.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.mlp.experts.255.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.35.input_layernorm.weight": "model-00092-of-000163.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.q_a_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.q_a_layernorm.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.q_b_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.kv_b_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.indexer.wq_b.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.indexer.wk.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.indexer.k_norm.weight": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.indexer.k_norm.bias": "model-00092-of-000163.safetensors", + "model.layers.36.self_attn.indexer.weights_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.gate.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00092-of-000163.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.128.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.128.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.128.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.129.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.129.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.129.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.130.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.130.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.130.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.131.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.131.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.131.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.132.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.132.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.132.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.133.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.133.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.133.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.134.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.134.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.134.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.135.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.135.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.135.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.136.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.136.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.136.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.137.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.137.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.137.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.138.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.138.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.138.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.139.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.139.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.139.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.140.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.140.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.140.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.141.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.141.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.141.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.142.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.142.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.142.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.143.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.143.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.143.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.144.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.144.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.144.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.145.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.145.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.145.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.146.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.146.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.146.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.147.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.147.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.147.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.148.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.148.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.148.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.149.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.149.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.149.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.150.gate_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.150.up_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.150.down_proj.weight": "model-00093-of-000163.safetensors", + "model.layers.36.mlp.experts.151.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.151.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.151.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.152.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.152.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.152.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.153.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.153.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.153.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.154.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.154.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.154.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.155.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.155.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.155.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.156.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.156.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.156.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.157.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.157.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.157.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.158.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.158.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.158.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.159.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.159.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.159.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.160.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.160.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.160.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.161.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.161.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.161.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.162.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.162.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.162.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.163.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.163.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.163.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.164.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.164.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.164.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.165.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.165.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.165.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.166.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.166.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.166.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.167.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.167.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.167.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.168.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.168.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.168.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.169.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.169.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.169.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.170.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.170.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.170.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.171.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.171.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.171.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.172.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.172.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.172.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.173.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.173.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.173.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.174.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.174.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.174.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.175.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.175.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.175.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.176.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.176.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.176.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.177.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.177.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.177.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.178.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.178.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.178.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.179.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.179.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.179.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.180.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.180.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.180.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.181.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.181.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.181.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.182.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.182.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.182.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.183.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.183.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.183.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.184.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.184.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.184.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.185.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.185.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.185.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.186.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.186.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.186.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.187.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.187.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.187.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.188.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.188.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.188.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.189.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.189.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.189.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.190.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.190.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.190.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.191.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.191.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.191.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.192.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.192.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.192.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.193.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.193.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.193.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.194.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.194.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.194.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.195.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.195.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.195.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.196.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.196.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.196.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.197.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.197.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.197.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.198.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.198.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.198.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.199.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.199.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.199.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.200.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.200.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.200.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.201.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.201.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.201.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.202.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.202.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.202.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.203.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.203.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.203.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.204.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.204.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.204.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.205.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.205.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.205.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.206.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.206.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.206.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.207.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.207.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.207.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.208.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.208.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.208.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.209.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.209.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.209.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.210.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.210.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.210.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.211.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.211.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.211.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.212.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.212.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.212.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.213.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.213.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.213.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.214.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.214.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.214.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.215.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.215.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.215.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.216.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.216.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.216.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.217.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.217.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.217.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.218.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.218.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.218.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.219.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.219.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.219.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.220.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.220.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.220.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.221.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.221.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.221.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.222.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.222.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.222.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.223.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.223.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.223.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.224.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.224.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.224.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.225.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.225.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.225.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.226.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.226.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.226.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.227.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.227.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.227.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.228.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.228.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.228.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.229.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.229.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.229.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.230.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.230.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.230.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.231.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.231.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.231.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.232.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.232.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.232.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.233.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.233.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.233.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.234.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.234.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.234.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.235.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.235.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.235.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.236.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.236.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.236.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.237.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.237.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.237.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.238.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.238.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.238.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.239.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.239.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.239.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.240.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.240.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.240.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.241.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.241.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.241.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.242.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.242.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.242.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.243.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.243.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.243.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.244.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.244.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.244.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.245.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.245.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.245.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.246.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.246.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.246.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.247.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.247.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.247.down_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.248.gate_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.248.up_proj.weight": "model-00094-of-000163.safetensors", + "model.layers.36.mlp.experts.248.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.249.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.249.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.249.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.250.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.250.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.250.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.251.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.251.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.251.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.252.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.252.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.252.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.253.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.253.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.253.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.254.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.254.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.254.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.255.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.255.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.mlp.experts.255.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.36.input_layernorm.weight": "model-00095-of-000163.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.q_a_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.q_a_layernorm.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.q_b_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.kv_a_proj_with_mqa.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.kv_a_layernorm.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.kv_b_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.indexer.wq_b.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.indexer.wk.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.indexer.k_norm.weight": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.indexer.k_norm.bias": "model-00095-of-000163.safetensors", + "model.layers.37.self_attn.indexer.weights_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.gate.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00095-of-000163.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.128.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.128.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.128.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.129.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.129.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.129.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.130.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.130.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.130.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.131.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.131.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.131.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.132.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.132.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.132.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.133.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.133.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.133.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.134.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.134.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.134.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.135.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.135.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.135.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.136.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.136.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.136.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.137.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.137.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.137.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.138.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.138.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.138.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.139.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.139.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.139.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.140.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.140.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.140.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.141.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.141.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.141.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.142.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.142.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.142.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.143.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.143.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.143.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.144.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.144.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.144.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.145.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.145.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.145.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.146.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.146.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.146.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.147.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.147.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.147.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.148.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.148.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.148.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.149.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.149.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.149.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.150.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.150.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.150.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.151.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.151.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.151.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.152.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.152.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.152.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.153.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.153.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.153.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.154.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.154.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.154.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.155.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.155.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.155.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.156.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.156.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.156.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.157.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.157.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.157.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.158.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.158.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.158.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.159.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.159.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.159.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.160.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.160.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.160.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.161.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.161.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.161.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.162.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.162.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.162.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.163.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.163.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.163.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.164.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.164.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.164.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.165.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.165.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.165.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.166.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.166.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.166.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.167.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.167.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.167.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.168.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.168.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.168.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.169.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.169.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.169.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.170.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.170.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.170.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.171.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.171.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.171.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.172.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.172.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.172.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.173.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.173.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.173.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.174.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.174.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.174.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.175.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.175.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.175.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.176.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.176.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.176.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.177.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.177.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.177.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.178.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.178.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.178.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.179.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.179.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.179.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.180.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.180.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.180.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.181.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.181.up_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.181.down_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.182.gate_proj.weight": "model-00096-of-000163.safetensors", + "model.layers.37.mlp.experts.182.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.182.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.183.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.183.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.183.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.184.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.184.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.184.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.185.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.185.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.185.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.186.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.186.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.186.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.187.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.187.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.187.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.188.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.188.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.188.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.189.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.189.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.189.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.190.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.190.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.190.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.191.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.191.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.191.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.192.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.192.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.192.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.193.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.193.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.193.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.194.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.194.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.194.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.195.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.195.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.195.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.196.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.196.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.196.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.197.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.197.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.197.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.198.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.198.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.198.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.199.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.199.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.199.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.200.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.200.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.200.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.201.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.201.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.201.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.202.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.202.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.202.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.203.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.203.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.203.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.204.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.204.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.204.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.205.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.205.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.205.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.206.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.206.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.206.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.207.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.207.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.207.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.208.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.208.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.208.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.209.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.209.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.209.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.210.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.210.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.210.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.211.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.211.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.211.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.212.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.212.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.212.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.213.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.213.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.213.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.214.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.214.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.214.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.215.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.215.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.215.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.216.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.216.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.216.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.217.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.217.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.217.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.218.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.218.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.218.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.219.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.219.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.219.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.220.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.220.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.220.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.221.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.221.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.221.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.222.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.222.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.222.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.223.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.223.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.223.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.224.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.224.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.224.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.225.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.225.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.225.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.226.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.226.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.226.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.227.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.227.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.227.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.228.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.228.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.228.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.229.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.229.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.229.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.230.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.230.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.230.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.231.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.231.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.231.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.232.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.232.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.232.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.233.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.233.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.233.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.234.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.234.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.234.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.235.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.235.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.235.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.236.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.236.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.236.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.237.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.237.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.237.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.238.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.238.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.238.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.239.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.239.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.239.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.240.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.240.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.240.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.241.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.241.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.241.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.242.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.242.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.242.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.243.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.243.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.243.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.244.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.244.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.244.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.245.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.245.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.245.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.246.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.246.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.246.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.247.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.247.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.247.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.248.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.248.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.248.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.249.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.249.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.249.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.250.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.250.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.250.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.251.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.251.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.251.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.252.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.252.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.252.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.253.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.253.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.253.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.254.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.254.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.254.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.255.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.255.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.mlp.experts.255.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.37.input_layernorm.weight": "model-00097-of-000163.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.q_a_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.q_a_layernorm.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.q_b_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.kv_a_proj_with_mqa.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.kv_a_layernorm.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.kv_b_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.indexer.wq_b.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.indexer.wk.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.indexer.k_norm.weight": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.indexer.k_norm.bias": "model-00097-of-000163.safetensors", + "model.layers.38.self_attn.indexer.weights_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.gate.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00097-of-000163.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00098-of-000163.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.128.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.128.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.128.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.129.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.129.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.129.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.130.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.130.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.130.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.131.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.131.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.131.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.132.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.132.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.132.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.133.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.133.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.133.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.134.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.134.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.134.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.135.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.135.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.135.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.136.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.136.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.136.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.137.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.137.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.137.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.138.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.138.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.138.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.139.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.139.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.139.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.140.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.140.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.140.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.141.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.141.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.141.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.142.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.142.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.142.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.143.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.143.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.143.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.144.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.144.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.144.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.145.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.145.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.145.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.146.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.146.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.146.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.147.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.147.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.147.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.148.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.148.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.148.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.149.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.149.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.149.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.150.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.150.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.150.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.151.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.151.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.151.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.152.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.152.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.152.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.153.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.153.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.153.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.154.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.154.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.154.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.155.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.155.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.155.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.156.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.156.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.156.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.157.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.157.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.157.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.158.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.158.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.158.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.159.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.159.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.159.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.160.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.160.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.160.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.161.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.161.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.161.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.162.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.162.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.162.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.163.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.163.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.163.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.164.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.164.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.164.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.165.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.165.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.165.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.166.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.166.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.166.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.167.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.167.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.167.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.168.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.168.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.168.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.169.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.169.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.169.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.170.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.170.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.170.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.171.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.171.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.171.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.172.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.172.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.172.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.173.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.173.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.173.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.174.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.174.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.174.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.175.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.175.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.175.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.176.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.176.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.176.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.177.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.177.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.177.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.178.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.178.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.178.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.179.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.179.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.179.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.180.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.180.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.180.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.181.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.181.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.181.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.182.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.182.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.182.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.183.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.183.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.183.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.184.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.184.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.184.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.185.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.185.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.185.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.186.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.186.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.186.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.187.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.187.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.187.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.188.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.188.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.188.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.189.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.189.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.189.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.190.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.190.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.190.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.191.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.191.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.191.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.192.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.192.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.192.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.193.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.193.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.193.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.194.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.194.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.194.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.195.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.195.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.195.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.196.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.196.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.196.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.197.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.197.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.197.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.198.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.198.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.198.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.199.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.199.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.199.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.200.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.200.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.200.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.201.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.201.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.201.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.202.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.202.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.202.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.203.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.203.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.203.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.204.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.204.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.204.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.205.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.205.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.205.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.206.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.206.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.206.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.207.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.207.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.207.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.208.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.208.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.208.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.209.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.209.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.209.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.210.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.210.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.210.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.211.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.211.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.211.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.212.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.212.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.212.down_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.213.gate_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.213.up_proj.weight": "model-00099-of-000163.safetensors", + "model.layers.38.mlp.experts.213.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.214.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.214.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.214.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.215.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.215.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.215.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.216.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.216.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.216.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.217.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.217.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.217.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.218.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.218.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.218.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.219.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.219.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.219.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.220.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.220.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.220.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.221.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.221.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.221.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.222.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.222.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.222.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.223.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.223.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.223.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.224.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.224.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.224.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.225.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.225.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.225.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.226.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.226.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.226.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.227.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.227.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.227.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.228.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.228.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.228.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.229.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.229.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.229.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.230.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.230.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.230.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.231.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.231.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.231.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.232.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.232.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.232.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.233.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.233.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.233.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.234.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.234.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.234.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.235.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.235.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.235.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.236.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.236.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.236.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.237.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.237.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.237.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.238.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.238.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.238.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.239.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.239.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.239.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.240.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.240.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.240.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.241.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.241.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.241.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.242.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.242.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.242.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.243.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.243.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.243.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.244.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.244.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.244.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.245.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.245.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.245.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.246.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.246.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.246.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.247.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.247.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.247.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.248.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.248.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.248.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.249.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.249.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.249.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.250.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.250.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.250.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.251.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.251.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.251.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.252.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.252.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.252.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.253.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.253.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.253.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.254.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.254.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.254.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.255.gate_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.255.up_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.mlp.experts.255.down_proj.weight": "model-00100-of-000163.safetensors", + "model.layers.38.input_layernorm.weight": "model-00100-of-000163.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00100-of-000163.safetensors", + "model.layers.39.self_attn.q_a_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.q_a_layernorm.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.q_b_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.kv_a_proj_with_mqa.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.kv_a_layernorm.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.kv_b_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.indexer.wq_b.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.indexer.wk.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.indexer.k_norm.weight": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.indexer.k_norm.bias": "model-00101-of-000163.safetensors", + "model.layers.39.self_attn.indexer.weights_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.gate.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00101-of-000163.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.128.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.128.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.128.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.129.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.129.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.129.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.130.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.130.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.130.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.131.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.131.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.131.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.132.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.132.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.132.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.133.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.133.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.133.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.134.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.134.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.134.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.135.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.135.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.135.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.136.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.136.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.136.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.137.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.137.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.137.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.138.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.138.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.138.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.139.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.139.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.139.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.140.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.140.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.140.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.141.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.141.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.141.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.142.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.142.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.142.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.143.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.143.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.143.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.144.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.144.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.144.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.145.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.145.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.145.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.146.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.146.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.146.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.147.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.147.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.147.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.148.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.148.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.148.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.149.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.149.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.149.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.150.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.150.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.150.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.151.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.151.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.151.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.152.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.152.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.152.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.153.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.153.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.153.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.154.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.154.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.154.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.155.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.155.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.155.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.156.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.156.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.156.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.157.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.157.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.157.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.158.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.158.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.158.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.159.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.159.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.159.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.160.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.160.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.160.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.161.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.161.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.161.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.162.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.162.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.162.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.163.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.163.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.163.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.164.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.164.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.164.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.165.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.165.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.165.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.166.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.166.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.166.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.167.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.167.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.167.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.168.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.168.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.168.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.169.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.169.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.169.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.170.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.170.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.170.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.171.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.171.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.171.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.172.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.172.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.172.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.173.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.173.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.173.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.174.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.174.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.174.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.175.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.175.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.175.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.176.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.176.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.176.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.177.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.177.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.177.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.178.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.178.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.178.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.179.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.179.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.179.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.180.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.180.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.180.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.181.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.181.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.181.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.182.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.182.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.182.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.183.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.183.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.183.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.184.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.184.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.184.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.185.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.185.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.185.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.186.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.186.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.186.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.187.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.187.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.187.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.188.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.188.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.188.down_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.189.gate_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.189.up_proj.weight": "model-00102-of-000163.safetensors", + "model.layers.39.mlp.experts.189.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.190.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.190.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.190.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.191.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.191.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.191.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.192.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.192.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.192.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.193.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.193.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.193.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.194.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.194.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.194.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.195.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.195.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.195.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.196.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.196.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.196.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.197.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.197.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.197.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.198.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.198.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.198.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.199.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.199.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.199.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.200.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.200.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.200.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.201.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.201.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.201.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.202.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.202.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.202.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.203.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.203.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.203.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.204.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.204.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.204.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.205.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.205.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.205.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.206.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.206.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.206.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.207.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.207.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.207.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.208.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.208.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.208.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.209.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.209.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.209.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.210.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.210.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.210.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.211.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.211.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.211.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.212.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.212.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.212.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.213.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.213.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.213.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.214.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.214.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.214.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.215.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.215.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.215.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.216.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.216.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.216.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.217.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.217.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.217.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.218.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.218.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.218.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.219.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.219.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.219.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.220.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.220.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.220.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.221.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.221.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.221.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.222.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.222.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.222.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.223.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.223.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.223.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.224.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.224.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.224.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.225.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.225.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.225.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.226.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.226.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.226.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.227.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.227.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.227.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.228.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.228.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.228.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.229.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.229.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.229.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.230.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.230.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.230.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.231.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.231.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.231.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.232.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.232.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.232.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.233.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.233.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.233.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.234.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.234.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.234.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.235.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.235.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.235.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.236.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.236.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.236.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.237.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.237.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.237.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.238.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.238.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.238.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.239.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.239.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.239.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.240.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.240.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.240.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.241.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.241.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.241.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.242.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.242.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.242.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.243.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.243.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.243.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.244.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.244.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.244.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.245.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.245.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.245.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.246.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.246.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.246.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.247.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.247.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.247.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.248.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.248.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.248.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.249.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.249.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.249.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.250.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.250.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.250.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.251.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.251.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.251.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.252.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.252.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.252.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.253.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.253.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.253.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.254.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.254.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.254.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.255.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.255.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.mlp.experts.255.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.39.input_layernorm.weight": "model-00103-of-000163.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.q_a_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.q_a_layernorm.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.q_b_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.kv_a_proj_with_mqa.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.kv_a_layernorm.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.kv_b_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.indexer.wq_b.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.indexer.wk.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.indexer.k_norm.weight": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.indexer.k_norm.bias": "model-00103-of-000163.safetensors", + "model.layers.40.self_attn.indexer.weights_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.gate.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00103-of-000163.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00104-of-000163.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.128.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.128.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.128.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.129.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.129.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.129.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.130.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.130.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.130.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.131.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.131.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.131.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.132.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.132.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.132.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.133.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.133.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.133.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.134.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.134.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.134.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.135.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.135.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.135.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.136.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.136.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.136.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.137.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.137.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.137.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.138.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.138.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.138.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.139.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.139.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.139.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.140.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.140.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.140.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.141.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.141.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.141.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.142.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.142.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.142.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.143.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.143.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.143.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.144.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.144.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.144.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.145.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.145.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.145.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.146.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.146.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.146.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.147.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.147.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.147.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.148.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.148.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.148.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.149.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.149.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.149.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.150.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.150.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.150.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.151.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.151.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.151.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.152.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.152.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.152.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.153.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.153.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.153.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.154.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.154.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.154.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.155.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.155.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.155.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.156.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.156.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.156.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.157.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.157.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.157.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.158.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.158.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.158.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.159.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.159.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.159.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.160.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.160.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.160.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.161.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.161.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.161.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.162.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.162.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.162.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.163.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.163.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.163.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.164.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.164.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.164.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.165.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.165.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.165.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.166.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.166.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.166.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.167.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.167.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.167.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.168.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.168.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.168.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.169.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.169.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.169.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.170.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.170.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.170.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.171.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.171.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.171.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.172.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.172.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.172.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.173.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.173.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.173.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.174.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.174.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.174.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.175.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.175.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.175.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.176.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.176.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.176.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.177.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.177.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.177.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.178.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.178.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.178.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.179.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.179.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.179.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.180.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.180.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.180.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.181.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.181.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.181.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.182.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.182.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.182.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.183.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.183.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.183.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.184.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.184.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.184.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.185.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.185.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.185.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.186.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.186.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.186.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.187.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.187.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.187.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.188.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.188.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.188.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.189.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.189.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.189.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.190.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.190.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.190.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.191.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.191.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.191.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.192.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.192.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.192.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.193.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.193.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.193.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.194.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.194.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.194.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.195.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.195.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.195.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.196.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.196.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.196.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.197.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.197.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.197.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.198.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.198.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.198.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.199.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.199.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.199.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.200.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.200.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.200.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.201.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.201.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.201.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.202.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.202.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.202.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.203.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.203.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.203.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.204.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.204.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.204.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.205.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.205.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.205.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.206.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.206.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.206.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.207.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.207.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.207.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.208.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.208.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.208.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.209.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.209.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.209.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.210.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.210.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.210.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.211.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.211.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.211.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.212.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.212.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.212.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.213.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.213.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.213.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.214.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.214.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.214.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.215.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.215.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.215.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.216.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.216.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.216.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.217.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.217.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.217.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.218.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.218.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.218.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.219.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.219.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.219.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.220.gate_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.220.up_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.220.down_proj.weight": "model-00105-of-000163.safetensors", + "model.layers.40.mlp.experts.221.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.221.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.221.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.222.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.222.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.222.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.223.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.223.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.223.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.224.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.224.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.224.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.225.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.225.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.225.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.226.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.226.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.226.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.227.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.227.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.227.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.228.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.228.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.228.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.229.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.229.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.229.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.230.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.230.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.230.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.231.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.231.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.231.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.232.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.232.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.232.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.233.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.233.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.233.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.234.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.234.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.234.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.235.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.235.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.235.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.236.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.236.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.236.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.237.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.237.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.237.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.238.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.238.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.238.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.239.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.239.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.239.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.240.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.240.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.240.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.241.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.241.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.241.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.242.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.242.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.242.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.243.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.243.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.243.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.244.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.244.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.244.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.245.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.245.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.245.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.246.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.246.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.246.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.247.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.247.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.247.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.248.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.248.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.248.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.249.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.249.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.249.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.250.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.250.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.250.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.251.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.251.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.251.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.252.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.252.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.252.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.253.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.253.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.253.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.254.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.254.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.254.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.255.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.255.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.mlp.experts.255.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.40.input_layernorm.weight": "model-00106-of-000163.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.q_a_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.q_a_layernorm.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.q_b_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.kv_a_proj_with_mqa.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.kv_a_layernorm.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.kv_b_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.indexer.wq_b.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.indexer.wk.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.indexer.k_norm.weight": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.indexer.k_norm.bias": "model-00106-of-000163.safetensors", + "model.layers.41.self_attn.indexer.weights_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.gate.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00106-of-000163.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.128.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.128.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.128.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.129.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.129.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.129.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.130.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.130.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.130.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.131.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.131.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.131.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.132.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.132.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.132.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.133.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.133.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.133.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.134.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.134.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.134.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.135.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.135.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.135.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.136.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.136.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.136.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.137.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.137.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.137.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.138.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.138.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.138.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.139.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.139.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.139.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.140.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.140.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.140.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.141.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.141.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.141.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.142.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.142.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.142.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.143.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.143.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.143.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.144.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.144.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.144.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.145.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.145.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.145.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.146.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.146.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.146.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.147.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.147.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.147.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.148.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.148.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.148.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.149.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.149.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.149.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.150.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.150.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.150.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.151.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.151.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.151.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.152.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.152.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.152.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.153.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.153.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.153.down_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.154.gate_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.154.up_proj.weight": "model-00107-of-000163.safetensors", + "model.layers.41.mlp.experts.154.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.155.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.155.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.155.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.156.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.156.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.156.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.157.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.157.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.157.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.158.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.158.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.158.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.159.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.159.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.159.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.160.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.160.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.160.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.161.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.161.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.161.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.162.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.162.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.162.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.163.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.163.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.163.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.164.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.164.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.164.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.165.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.165.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.165.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.166.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.166.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.166.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.167.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.167.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.167.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.168.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.168.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.168.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.169.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.169.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.169.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.170.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.170.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.170.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.171.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.171.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.171.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.172.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.172.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.172.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.173.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.173.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.173.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.174.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.174.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.174.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.175.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.175.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.175.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.176.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.176.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.176.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.177.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.177.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.177.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.178.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.178.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.178.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.179.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.179.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.179.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.180.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.180.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.180.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.181.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.181.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.181.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.182.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.182.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.182.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.183.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.183.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.183.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.184.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.184.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.184.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.185.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.185.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.185.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.186.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.186.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.186.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.187.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.187.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.187.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.188.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.188.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.188.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.189.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.189.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.189.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.190.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.190.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.190.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.191.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.191.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.191.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.192.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.192.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.192.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.193.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.193.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.193.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.194.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.194.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.194.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.195.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.195.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.195.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.196.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.196.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.196.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.197.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.197.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.197.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.198.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.198.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.198.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.199.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.199.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.199.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.200.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.200.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.200.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.201.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.201.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.201.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.202.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.202.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.202.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.203.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.203.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.203.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.204.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.204.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.204.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.205.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.205.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.205.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.206.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.206.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.206.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.207.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.207.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.207.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.208.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.208.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.208.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.209.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.209.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.209.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.210.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.210.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.210.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.211.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.211.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.211.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.212.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.212.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.212.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.213.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.213.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.213.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.214.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.214.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.214.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.215.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.215.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.215.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.216.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.216.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.216.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.217.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.217.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.217.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.218.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.218.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.218.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.219.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.219.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.219.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.220.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.220.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.220.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.221.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.221.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.221.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.222.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.222.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.222.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.223.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.223.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.223.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.224.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.224.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.224.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.225.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.225.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.225.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.226.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.226.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.226.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.227.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.227.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.227.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.228.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.228.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.228.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.229.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.229.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.229.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.230.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.230.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.230.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.231.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.231.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.231.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.232.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.232.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.232.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.233.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.233.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.233.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.234.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.234.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.234.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.235.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.235.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.235.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.236.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.236.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.236.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.237.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.237.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.237.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.238.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.238.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.238.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.239.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.239.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.239.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.240.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.240.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.240.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.241.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.241.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.241.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.242.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.242.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.242.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.243.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.243.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.243.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.244.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.244.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.244.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.245.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.245.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.245.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.246.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.246.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.246.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.247.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.247.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.247.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.248.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.248.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.248.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.249.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.249.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.249.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.250.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.250.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.250.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.251.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.251.up_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.251.down_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.252.gate_proj.weight": "model-00108-of-000163.safetensors", + "model.layers.41.mlp.experts.252.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.252.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.253.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.253.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.253.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.254.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.254.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.254.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.255.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.255.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.mlp.experts.255.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.41.input_layernorm.weight": "model-00109-of-000163.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.q_a_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.q_a_layernorm.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.q_b_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.kv_a_proj_with_mqa.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.kv_a_layernorm.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.kv_b_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.indexer.wq_b.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.indexer.wk.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.indexer.k_norm.weight": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.indexer.k_norm.bias": "model-00109-of-000163.safetensors", + "model.layers.42.self_attn.indexer.weights_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.gate.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00109-of-000163.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.128.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.128.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.128.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.129.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.129.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.129.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.130.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.130.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.130.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.131.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.131.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.131.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.132.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.132.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.132.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.133.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.133.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.133.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.134.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.134.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.134.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.135.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.135.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.135.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.136.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.136.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.136.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.137.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.137.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.137.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.138.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.138.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.138.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.139.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.139.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.139.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.140.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.140.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.140.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.141.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.141.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.141.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.142.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.142.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.142.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.143.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.143.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.143.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.144.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.144.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.144.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.145.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.145.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.145.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.146.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.146.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.146.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.147.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.147.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.147.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.148.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.148.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.148.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.149.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.149.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.149.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.150.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.150.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.150.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.151.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.151.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.151.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.152.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.152.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.152.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.153.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.153.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.153.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.154.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.154.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.154.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.155.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.155.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.155.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.156.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.156.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.156.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.157.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.157.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.157.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.158.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.158.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.158.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.159.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.159.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.159.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.160.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.160.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.160.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.161.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.161.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.161.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.162.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.162.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.162.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.163.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.163.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.163.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.164.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.164.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.164.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.165.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.165.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.165.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.166.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.166.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.166.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.167.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.167.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.167.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.168.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.168.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.168.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.169.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.169.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.169.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.170.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.170.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.170.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.171.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.171.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.171.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.172.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.172.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.172.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.173.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.173.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.173.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.174.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.174.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.174.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.175.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.175.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.175.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.176.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.176.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.176.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.177.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.177.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.177.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.178.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.178.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.178.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.179.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.179.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.179.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.180.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.180.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.180.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.181.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.181.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.181.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.182.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.182.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.182.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.183.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.183.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.183.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.184.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.184.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.184.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.185.gate_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.185.up_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.185.down_proj.weight": "model-00110-of-000163.safetensors", + "model.layers.42.mlp.experts.186.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.186.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.186.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.187.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.187.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.187.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.188.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.188.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.188.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.189.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.189.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.189.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.190.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.190.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.190.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.191.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.191.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.191.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.192.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.192.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.192.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.193.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.193.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.193.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.194.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.194.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.194.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.195.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.195.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.195.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.196.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.196.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.196.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.197.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.197.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.197.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.198.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.198.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.198.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.199.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.199.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.199.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.200.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.200.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.200.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.201.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.201.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.201.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.202.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.202.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.202.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.203.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.203.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.203.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.204.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.204.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.204.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.205.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.205.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.205.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.206.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.206.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.206.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.207.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.207.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.207.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.208.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.208.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.208.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.209.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.209.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.209.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.210.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.210.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.210.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.211.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.211.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.211.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.212.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.212.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.212.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.213.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.213.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.213.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.214.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.214.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.214.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.215.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.215.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.215.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.216.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.216.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.216.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.217.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.217.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.217.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.218.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.218.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.218.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.219.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.219.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.219.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.220.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.220.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.220.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.221.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.221.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.221.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.222.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.222.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.222.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.223.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.223.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.223.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.224.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.224.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.224.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.225.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.225.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.225.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.226.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.226.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.226.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.227.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.227.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.227.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.228.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.228.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.228.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.229.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.229.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.229.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.230.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.230.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.230.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.231.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.231.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.231.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.232.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.232.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.232.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.233.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.233.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.233.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.234.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.234.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.234.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.235.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.235.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.235.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.236.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.236.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.236.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.237.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.237.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.237.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.238.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.238.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.238.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.239.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.239.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.239.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.240.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.240.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.240.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.241.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.241.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.241.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.242.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.242.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.242.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.243.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.243.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.243.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.244.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.244.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.244.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.245.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.245.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.245.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.246.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.246.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.246.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.247.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.247.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.247.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.248.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.248.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.248.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.249.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.249.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.249.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.250.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.250.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.250.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.251.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.251.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.251.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.252.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.252.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.252.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.253.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.253.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.253.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.254.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.254.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.254.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.255.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.255.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.mlp.experts.255.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.42.input_layernorm.weight": "model-00111-of-000163.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.q_a_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.q_a_layernorm.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.q_b_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.kv_a_proj_with_mqa.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.kv_a_layernorm.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.kv_b_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.indexer.wq_b.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.indexer.wk.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.indexer.k_norm.weight": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.indexer.k_norm.bias": "model-00111-of-000163.safetensors", + "model.layers.43.self_attn.indexer.weights_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.gate.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00111-of-000163.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00112-of-000163.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.128.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.128.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.128.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.129.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.129.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.129.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.130.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.130.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.130.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.131.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.131.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.131.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.132.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.132.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.132.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.133.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.133.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.133.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.134.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.134.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.134.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.135.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.135.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.135.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.136.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.136.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.136.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.137.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.137.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.137.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.138.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.138.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.138.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.139.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.139.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.139.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.140.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.140.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.140.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.141.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.141.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.141.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.142.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.142.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.142.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.143.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.143.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.143.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.144.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.144.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.144.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.145.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.145.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.145.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.146.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.146.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.146.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.147.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.147.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.147.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.148.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.148.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.148.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.149.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.149.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.149.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.150.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.150.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.150.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.151.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.151.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.151.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.152.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.152.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.152.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.153.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.153.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.153.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.154.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.154.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.154.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.155.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.155.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.155.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.156.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.156.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.156.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.157.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.157.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.157.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.158.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.158.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.158.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.159.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.159.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.159.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.160.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.160.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.160.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.161.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.161.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.161.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.162.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.162.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.162.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.163.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.163.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.163.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.164.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.164.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.164.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.165.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.165.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.165.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.166.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.166.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.166.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.167.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.167.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.167.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.168.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.168.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.168.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.169.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.169.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.169.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.170.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.170.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.170.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.171.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.171.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.171.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.172.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.172.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.172.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.173.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.173.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.173.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.174.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.174.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.174.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.175.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.175.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.175.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.176.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.176.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.176.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.177.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.177.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.177.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.178.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.178.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.178.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.179.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.179.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.179.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.180.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.180.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.180.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.181.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.181.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.181.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.182.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.182.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.182.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.183.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.183.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.183.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.184.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.184.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.184.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.185.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.185.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.185.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.186.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.186.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.186.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.187.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.187.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.187.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.188.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.188.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.188.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.189.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.189.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.189.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.190.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.190.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.190.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.191.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.191.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.191.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.192.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.192.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.192.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.193.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.193.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.193.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.194.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.194.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.194.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.195.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.195.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.195.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.196.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.196.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.196.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.197.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.197.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.197.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.198.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.198.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.198.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.199.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.199.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.199.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.200.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.200.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.200.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.201.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.201.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.201.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.202.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.202.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.202.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.203.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.203.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.203.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.204.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.204.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.204.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.205.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.205.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.205.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.206.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.206.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.206.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.207.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.207.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.207.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.208.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.208.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.208.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.209.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.209.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.209.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.210.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.210.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.210.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.211.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.211.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.211.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.212.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.212.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.212.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.213.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.213.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.213.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.214.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.214.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.214.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.215.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.215.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.215.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.216.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.216.up_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.216.down_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.217.gate_proj.weight": "model-00113-of-000163.safetensors", + "model.layers.43.mlp.experts.217.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.217.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.218.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.218.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.218.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.219.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.219.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.219.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.220.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.220.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.220.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.221.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.221.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.221.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.222.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.222.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.222.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.223.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.223.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.223.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.224.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.224.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.224.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.225.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.225.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.225.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.226.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.226.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.226.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.227.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.227.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.227.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.228.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.228.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.228.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.229.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.229.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.229.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.230.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.230.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.230.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.231.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.231.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.231.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.232.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.232.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.232.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.233.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.233.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.233.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.234.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.234.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.234.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.235.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.235.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.235.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.236.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.236.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.236.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.237.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.237.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.237.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.238.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.238.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.238.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.239.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.239.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.239.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.240.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.240.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.240.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.241.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.241.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.241.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.242.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.242.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.242.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.243.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.243.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.243.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.244.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.244.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.244.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.245.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.245.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.245.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.246.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.246.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.246.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.247.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.247.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.247.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.248.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.248.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.248.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.249.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.249.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.249.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.250.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.250.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.250.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.251.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.251.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.251.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.252.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.252.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.252.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.253.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.253.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.253.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.254.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.254.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.254.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.255.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.255.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.mlp.experts.255.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.43.input_layernorm.weight": "model-00114-of-000163.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.q_a_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.q_a_layernorm.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.q_b_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.kv_a_proj_with_mqa.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.kv_a_layernorm.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.kv_b_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.indexer.wq_b.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.indexer.wk.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.indexer.k_norm.weight": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.indexer.k_norm.bias": "model-00114-of-000163.safetensors", + "model.layers.44.self_attn.indexer.weights_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.gate.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00114-of-000163.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.128.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.128.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.128.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.129.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.129.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.129.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.130.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.130.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.130.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.131.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.131.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.131.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.132.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.132.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.132.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.133.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.133.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.133.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.134.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.134.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.134.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.135.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.135.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.135.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.136.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.136.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.136.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.137.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.137.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.137.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.138.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.138.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.138.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.139.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.139.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.139.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.140.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.140.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.140.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.141.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.141.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.141.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.142.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.142.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.142.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.143.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.143.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.143.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.144.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.144.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.144.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.145.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.145.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.145.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.146.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.146.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.146.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.147.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.147.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.147.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.148.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.148.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.148.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.149.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.149.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.149.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.150.gate_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.150.up_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.150.down_proj.weight": "model-00115-of-000163.safetensors", + "model.layers.44.mlp.experts.151.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.151.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.151.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.152.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.152.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.152.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.153.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.153.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.153.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.154.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.154.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.154.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.155.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.155.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.155.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.156.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.156.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.156.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.157.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.157.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.157.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.158.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.158.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.158.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.159.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.159.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.159.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.160.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.160.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.160.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.161.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.161.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.161.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.162.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.162.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.162.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.163.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.163.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.163.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.164.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.164.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.164.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.165.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.165.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.165.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.166.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.166.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.166.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.167.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.167.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.167.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.168.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.168.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.168.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.169.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.169.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.169.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.170.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.170.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.170.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.171.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.171.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.171.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.172.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.172.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.172.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.173.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.173.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.173.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.174.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.174.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.174.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.175.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.175.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.175.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.176.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.176.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.176.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.177.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.177.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.177.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.178.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.178.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.178.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.179.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.179.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.179.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.180.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.180.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.180.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.181.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.181.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.181.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.182.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.182.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.182.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.183.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.183.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.183.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.184.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.184.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.184.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.185.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.185.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.185.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.186.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.186.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.186.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.187.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.187.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.187.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.188.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.188.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.188.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.189.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.189.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.189.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.190.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.190.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.190.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.191.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.191.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.191.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.192.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.192.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.192.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.193.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.193.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.193.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.194.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.194.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.194.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.195.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.195.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.195.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.196.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.196.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.196.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.197.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.197.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.197.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.198.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.198.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.198.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.199.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.199.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.199.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.200.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.200.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.200.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.201.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.201.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.201.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.202.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.202.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.202.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.203.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.203.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.203.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.204.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.204.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.204.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.205.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.205.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.205.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.206.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.206.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.206.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.207.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.207.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.207.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.208.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.208.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.208.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.209.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.209.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.209.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.210.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.210.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.210.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.211.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.211.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.211.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.212.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.212.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.212.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.213.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.213.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.213.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.214.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.214.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.214.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.215.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.215.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.215.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.216.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.216.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.216.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.217.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.217.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.217.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.218.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.218.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.218.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.219.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.219.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.219.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.220.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.220.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.220.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.221.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.221.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.221.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.222.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.222.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.222.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.223.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.223.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.223.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.224.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.224.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.224.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.225.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.225.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.225.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.226.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.226.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.226.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.227.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.227.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.227.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.228.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.228.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.228.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.229.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.229.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.229.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.230.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.230.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.230.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.231.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.231.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.231.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.232.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.232.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.232.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.233.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.233.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.233.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.234.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.234.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.234.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.235.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.235.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.235.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.236.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.236.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.236.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.237.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.237.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.237.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.238.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.238.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.238.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.239.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.239.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.239.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.240.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.240.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.240.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.241.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.241.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.241.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.242.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.242.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.242.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.243.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.243.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.243.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.244.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.244.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.244.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.245.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.245.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.245.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.246.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.246.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.246.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.247.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.247.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.247.down_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.248.gate_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.248.up_proj.weight": "model-00116-of-000163.safetensors", + "model.layers.44.mlp.experts.248.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.249.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.249.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.249.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.250.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.250.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.250.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.251.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.251.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.251.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.252.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.252.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.252.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.253.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.253.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.253.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.254.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.254.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.254.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.255.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.255.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.mlp.experts.255.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.44.input_layernorm.weight": "model-00117-of-000163.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.q_a_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.q_a_layernorm.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.q_b_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.kv_a_proj_with_mqa.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.kv_a_layernorm.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.kv_b_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.indexer.wq_b.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.indexer.wk.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.indexer.k_norm.weight": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.indexer.k_norm.bias": "model-00117-of-000163.safetensors", + "model.layers.45.self_attn.indexer.weights_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.gate.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00117-of-000163.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.128.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.128.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.128.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.129.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.129.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.129.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.130.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.130.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.130.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.131.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.131.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.131.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.132.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.132.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.132.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.133.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.133.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.133.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.134.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.134.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.134.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.135.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.135.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.135.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.136.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.136.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.136.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.137.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.137.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.137.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.138.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.138.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.138.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.139.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.139.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.139.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.140.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.140.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.140.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.141.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.141.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.141.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.142.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.142.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.142.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.143.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.143.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.143.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.144.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.144.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.144.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.145.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.145.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.145.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.146.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.146.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.146.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.147.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.147.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.147.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.148.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.148.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.148.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.149.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.149.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.149.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.150.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.150.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.150.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.151.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.151.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.151.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.152.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.152.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.152.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.153.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.153.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.153.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.154.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.154.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.154.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.155.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.155.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.155.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.156.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.156.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.156.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.157.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.157.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.157.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.158.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.158.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.158.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.159.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.159.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.159.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.160.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.160.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.160.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.161.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.161.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.161.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.162.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.162.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.162.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.163.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.163.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.163.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.164.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.164.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.164.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.165.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.165.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.165.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.166.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.166.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.166.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.167.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.167.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.167.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.168.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.168.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.168.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.169.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.169.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.169.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.170.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.170.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.170.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.171.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.171.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.171.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.172.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.172.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.172.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.173.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.173.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.173.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.174.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.174.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.174.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.175.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.175.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.175.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.176.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.176.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.176.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.177.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.177.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.177.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.178.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.178.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.178.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.179.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.179.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.179.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.180.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.180.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.180.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.181.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.181.up_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.181.down_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.182.gate_proj.weight": "model-00118-of-000163.safetensors", + "model.layers.45.mlp.experts.182.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.182.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.183.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.183.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.183.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.184.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.184.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.184.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.185.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.185.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.185.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.186.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.186.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.186.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.187.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.187.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.187.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.188.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.188.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.188.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.189.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.189.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.189.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.190.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.190.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.190.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.191.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.191.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.191.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.192.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.192.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.192.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.193.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.193.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.193.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.194.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.194.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.194.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.195.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.195.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.195.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.196.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.196.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.196.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.197.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.197.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.197.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.198.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.198.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.198.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.199.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.199.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.199.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.200.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.200.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.200.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.201.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.201.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.201.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.202.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.202.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.202.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.203.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.203.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.203.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.204.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.204.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.204.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.205.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.205.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.205.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.206.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.206.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.206.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.207.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.207.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.207.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.208.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.208.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.208.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.209.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.209.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.209.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.210.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.210.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.210.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.211.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.211.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.211.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.212.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.212.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.212.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.213.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.213.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.213.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.214.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.214.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.214.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.215.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.215.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.215.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.216.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.216.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.216.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.217.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.217.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.217.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.218.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.218.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.218.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.219.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.219.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.219.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.220.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.220.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.220.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.221.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.221.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.221.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.222.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.222.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.222.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.223.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.223.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.223.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.224.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.224.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.224.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.225.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.225.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.225.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.226.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.226.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.226.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.227.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.227.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.227.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.228.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.228.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.228.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.229.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.229.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.229.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.230.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.230.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.230.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.231.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.231.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.231.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.232.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.232.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.232.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.233.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.233.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.233.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.234.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.234.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.234.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.235.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.235.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.235.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.236.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.236.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.236.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.237.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.237.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.237.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.238.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.238.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.238.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.239.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.239.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.239.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.240.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.240.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.240.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.241.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.241.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.241.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.242.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.242.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.242.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.243.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.243.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.243.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.244.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.244.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.244.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.245.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.245.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.245.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.246.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.246.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.246.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.247.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.247.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.247.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.248.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.248.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.248.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.249.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.249.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.249.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.250.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.250.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.250.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.251.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.251.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.251.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.252.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.252.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.252.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.253.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.253.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.253.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.254.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.254.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.254.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.255.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.255.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.mlp.experts.255.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.45.input_layernorm.weight": "model-00119-of-000163.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.q_a_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.q_a_layernorm.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.q_b_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.kv_a_proj_with_mqa.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.kv_a_layernorm.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.kv_b_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.indexer.wq_b.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.indexer.wk.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.indexer.k_norm.weight": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.indexer.k_norm.bias": "model-00119-of-000163.safetensors", + "model.layers.46.self_attn.indexer.weights_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.gate.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.gate.e_score_correction_bias": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.shared_experts.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.shared_experts.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.shared_experts.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.0.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.0.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.0.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.1.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.1.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.1.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.2.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.2.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.2.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.3.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.3.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.3.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.4.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.4.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.4.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.5.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.5.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.5.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.6.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.6.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.6.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.7.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.7.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.7.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.8.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.8.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.8.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.9.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.9.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.9.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.10.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.10.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.10.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.11.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.11.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.11.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.12.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.12.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.12.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.13.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.13.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.13.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.14.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.14.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.14.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.15.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.15.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.15.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.16.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.16.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.16.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.17.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.17.up_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.17.down_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.18.gate_proj.weight": "model-00119-of-000163.safetensors", + "model.layers.46.mlp.experts.18.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.18.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.19.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.19.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.19.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.20.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.20.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.20.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.21.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.21.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.21.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.22.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.22.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.22.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.23.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.23.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.23.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.24.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.24.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.24.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.25.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.25.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.25.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.26.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.26.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.26.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.27.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.27.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.27.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.28.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.28.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.28.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.29.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.29.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.29.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.30.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.30.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.30.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.31.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.31.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.31.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.32.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.32.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.32.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.33.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.33.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.33.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.34.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.34.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.34.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.35.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.35.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.35.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.36.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.36.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.36.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.37.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.37.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.37.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.38.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.38.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.38.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.39.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.39.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.39.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.40.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.40.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.40.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.41.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.41.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.41.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.42.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.42.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.42.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.43.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.43.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.43.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.44.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.44.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.44.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.45.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.45.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.45.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.46.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.46.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.46.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.47.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.47.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.47.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.48.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.48.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.48.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.49.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.49.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.49.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.50.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.50.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.50.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.51.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.51.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.51.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.52.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.52.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.52.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.53.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.53.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.53.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.54.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.54.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.54.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.55.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.55.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.55.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.56.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.56.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.56.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.57.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.57.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.57.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.58.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.58.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.58.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.59.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.59.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.59.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.60.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.60.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.60.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.61.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.61.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.61.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.62.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.62.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.62.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.63.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.63.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.63.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.64.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.64.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.64.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.65.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.65.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.65.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.66.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.66.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.66.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.67.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.67.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.67.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.68.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.68.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.68.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.69.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.69.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.69.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.70.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.70.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.70.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.71.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.71.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.71.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.72.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.72.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.72.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.73.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.73.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.73.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.74.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.74.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.74.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.75.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.75.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.75.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.76.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.76.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.76.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.77.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.77.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.77.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.78.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.78.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.78.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.79.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.79.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.79.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.80.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.80.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.80.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.81.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.81.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.81.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.82.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.82.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.82.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.83.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.83.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.83.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.84.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.84.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.84.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.85.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.85.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.85.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.86.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.86.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.86.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.87.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.87.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.87.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.88.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.88.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.88.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.89.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.89.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.89.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.90.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.90.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.90.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.91.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.91.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.91.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.92.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.92.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.92.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.93.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.93.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.93.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.94.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.94.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.94.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.95.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.95.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.95.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.96.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.96.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.96.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.97.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.97.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.97.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.98.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.98.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.98.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.99.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.99.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.99.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.100.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.100.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.100.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.101.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.101.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.101.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.102.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.102.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.102.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.103.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.103.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.103.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.104.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.104.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.104.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.105.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.105.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.105.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.106.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.106.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.106.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.107.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.107.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.107.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.108.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.108.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.108.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.109.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.109.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.109.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.110.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.110.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.110.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.111.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.111.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.111.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.112.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.112.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.112.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.113.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.113.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.113.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.114.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.114.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.114.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.115.gate_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.115.up_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.115.down_proj.weight": "model-00120-of-000163.safetensors", + "model.layers.46.mlp.experts.116.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.116.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.116.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.117.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.117.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.117.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.118.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.118.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.118.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.119.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.119.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.119.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.120.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.120.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.120.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.121.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.121.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.121.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.122.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.122.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.122.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.123.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.123.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.123.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.124.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.124.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.124.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.125.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.125.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.125.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.126.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.126.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.126.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.127.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.127.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.127.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.128.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.128.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.128.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.129.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.129.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.129.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.130.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.130.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.130.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.131.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.131.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.131.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.132.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.132.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.132.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.133.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.133.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.133.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.134.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.134.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.134.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.135.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.135.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.135.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.136.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.136.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.136.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.137.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.137.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.137.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.138.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.138.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.138.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.139.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.139.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.139.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.140.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.140.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.140.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.141.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.141.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.141.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.142.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.142.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.142.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.143.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.143.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.143.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.144.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.144.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.144.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.145.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.145.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.145.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.146.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.146.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.146.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.147.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.147.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.147.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.148.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.148.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.148.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.149.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.149.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.149.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.150.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.150.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.150.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.151.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.151.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.151.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.152.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.152.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.152.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.153.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.153.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.153.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.154.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.154.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.154.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.155.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.155.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.155.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.156.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.156.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.156.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.157.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.157.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.157.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.158.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.158.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.158.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.159.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.159.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.159.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.160.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.160.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.160.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.161.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.161.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.161.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.162.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.162.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.162.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.163.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.163.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.163.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.164.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.164.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.164.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.165.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.165.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.165.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.166.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.166.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.166.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.167.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.167.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.167.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.168.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.168.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.168.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.169.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.169.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.169.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.170.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.170.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.170.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.171.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.171.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.171.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.172.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.172.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.172.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.173.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.173.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.173.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.174.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.174.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.174.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.175.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.175.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.175.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.176.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.176.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.176.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.177.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.177.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.177.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.178.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.178.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.178.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.179.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.179.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.179.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.180.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.180.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.180.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.181.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.181.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.181.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.182.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.182.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.182.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.183.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.183.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.183.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.184.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.184.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.184.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.185.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.185.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.185.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.186.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.186.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.186.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.187.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.187.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.187.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.188.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.188.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.188.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.189.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.189.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.189.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.190.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.190.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.190.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.191.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.191.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.191.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.192.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.192.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.192.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.193.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.193.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.193.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.194.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.194.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.194.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.195.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.195.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.195.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.196.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.196.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.196.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.197.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.197.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.197.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.198.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.198.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.198.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.199.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.199.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.199.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.200.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.200.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.200.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.201.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.201.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.201.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.202.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.202.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.202.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.203.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.203.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.203.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.204.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.204.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.204.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.205.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.205.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.205.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.206.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.206.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.206.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.207.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.207.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.207.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.208.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.208.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.208.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.209.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.209.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.209.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.210.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.210.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.210.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.211.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.211.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.211.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.212.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.212.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.212.down_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.213.gate_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.213.up_proj.weight": "model-00121-of-000163.safetensors", + "model.layers.46.mlp.experts.213.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.214.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.214.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.214.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.215.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.215.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.215.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.216.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.216.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.216.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.217.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.217.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.217.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.218.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.218.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.218.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.219.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.219.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.219.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.220.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.220.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.220.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.221.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.221.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.221.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.222.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.222.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.222.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.223.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.223.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.223.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.224.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.224.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.224.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.225.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.225.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.225.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.226.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.226.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.226.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.227.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.227.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.227.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.228.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.228.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.228.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.229.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.229.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.229.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.230.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.230.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.230.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.231.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.231.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.231.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.232.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.232.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.232.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.233.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.233.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.233.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.234.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.234.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.234.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.235.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.235.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.235.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.236.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.236.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.236.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.237.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.237.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.237.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.238.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.238.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.238.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.239.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.239.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.239.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.240.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.240.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.240.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.241.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.241.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.241.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.242.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.242.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.242.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.243.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.243.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.243.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.244.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.244.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.244.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.245.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.245.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.245.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.246.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.246.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.246.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.247.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.247.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.247.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.248.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.248.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.248.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.249.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.249.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.249.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.250.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.250.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.250.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.251.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.251.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.251.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.252.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.252.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.252.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.253.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.253.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.253.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.254.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.254.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.254.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.255.gate_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.255.up_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.mlp.experts.255.down_proj.weight": "model-00122-of-000163.safetensors", + "model.layers.46.input_layernorm.weight": "model-00122-of-000163.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00122-of-000163.safetensors", + "model.layers.47.self_attn.q_a_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.q_a_layernorm.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.q_b_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.kv_a_proj_with_mqa.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.kv_a_layernorm.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.kv_b_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.indexer.wq_b.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.indexer.wk.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.indexer.k_norm.weight": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.indexer.k_norm.bias": "model-00123-of-000163.safetensors", + "model.layers.47.self_attn.indexer.weights_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.gate.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.gate.e_score_correction_bias": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.shared_experts.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.shared_experts.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.shared_experts.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.0.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.0.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.0.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.1.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.1.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.1.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.2.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.2.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.2.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.3.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.3.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.3.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.4.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.4.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.4.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.5.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.5.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.5.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.6.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.6.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.6.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.7.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.7.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.7.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.8.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.8.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.8.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.9.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.9.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.9.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.10.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.10.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.10.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.11.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.11.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.11.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.12.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.12.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.12.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.13.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.13.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.13.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.14.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.14.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.14.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.15.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.15.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.15.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.16.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.16.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.16.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.17.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.17.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.17.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.18.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.18.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.18.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.19.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.19.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.19.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.20.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.20.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.20.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.21.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.21.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.21.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.22.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.22.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.22.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.23.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.23.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.23.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.24.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.24.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.24.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.25.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.25.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.25.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.26.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.26.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.26.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.27.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.27.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.27.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.28.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.28.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.28.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.29.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.29.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.29.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.30.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.30.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.30.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.31.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.31.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.31.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.32.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.32.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.32.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.33.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.33.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.33.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.34.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.34.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.34.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.35.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.35.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.35.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.36.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.36.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.36.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.37.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.37.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.37.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.38.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.38.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.38.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.39.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.39.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.39.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.40.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.40.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.40.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.41.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.41.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.41.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.42.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.42.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.42.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.43.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.43.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.43.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.44.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.44.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.44.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.45.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.45.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.45.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.46.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.46.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.46.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.47.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.47.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.47.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.48.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.48.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.48.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.49.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.49.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.49.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.50.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.50.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.50.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.51.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.51.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.51.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.52.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.52.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.52.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.53.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.53.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.53.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.54.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.54.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.54.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.55.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.55.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.55.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.56.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.56.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.56.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.57.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.57.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.57.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.58.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.58.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.58.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.59.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.59.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.59.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.60.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.60.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.60.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.61.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.61.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.61.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.62.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.62.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.62.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.63.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.63.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.63.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.64.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.64.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.64.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.65.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.65.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.65.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.66.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.66.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.66.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.67.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.67.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.67.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.68.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.68.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.68.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.69.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.69.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.69.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.70.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.70.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.70.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.71.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.71.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.71.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.72.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.72.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.72.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.73.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.73.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.73.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.74.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.74.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.74.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.75.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.75.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.75.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.76.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.76.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.76.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.77.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.77.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.77.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.78.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.78.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.78.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.79.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.79.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.79.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.80.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.80.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.80.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.81.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.81.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.81.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.82.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.82.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.82.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.83.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.83.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.83.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.84.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.84.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.84.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.85.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.85.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.85.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.86.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.86.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.86.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.87.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.87.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.87.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.88.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.88.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.88.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.89.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.89.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.89.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.90.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.90.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.90.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.91.gate_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.91.up_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.91.down_proj.weight": "model-00123-of-000163.safetensors", + "model.layers.47.mlp.experts.92.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.92.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.92.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.93.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.93.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.93.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.94.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.94.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.94.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.95.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.95.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.95.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.96.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.96.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.96.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.97.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.97.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.97.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.98.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.98.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.98.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.99.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.99.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.99.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.100.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.100.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.100.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.101.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.101.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.101.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.102.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.102.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.102.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.103.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.103.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.103.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.104.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.104.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.104.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.105.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.105.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.105.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.106.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.106.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.106.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.107.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.107.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.107.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.108.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.108.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.108.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.109.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.109.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.109.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.110.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.110.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.110.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.111.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.111.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.111.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.112.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.112.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.112.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.113.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.113.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.113.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.114.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.114.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.114.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.115.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.115.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.115.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.116.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.116.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.116.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.117.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.117.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.117.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.118.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.118.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.118.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.119.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.119.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.119.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.120.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.120.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.120.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.121.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.121.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.121.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.122.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.122.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.122.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.123.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.123.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.123.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.124.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.124.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.124.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.125.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.125.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.125.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.126.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.126.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.126.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.127.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.127.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.127.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.128.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.128.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.128.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.129.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.129.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.129.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.130.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.130.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.130.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.131.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.131.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.131.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.132.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.132.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.132.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.133.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.133.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.133.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.134.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.134.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.134.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.135.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.135.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.135.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.136.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.136.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.136.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.137.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.137.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.137.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.138.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.138.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.138.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.139.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.139.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.139.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.140.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.140.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.140.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.141.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.141.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.141.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.142.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.142.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.142.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.143.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.143.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.143.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.144.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.144.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.144.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.145.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.145.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.145.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.146.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.146.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.146.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.147.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.147.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.147.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.148.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.148.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.148.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.149.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.149.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.149.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.150.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.150.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.150.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.151.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.151.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.151.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.152.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.152.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.152.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.153.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.153.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.153.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.154.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.154.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.154.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.155.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.155.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.155.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.156.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.156.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.156.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.157.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.157.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.157.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.158.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.158.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.158.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.159.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.159.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.159.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.160.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.160.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.160.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.161.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.161.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.161.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.162.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.162.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.162.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.163.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.163.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.163.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.164.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.164.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.164.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.165.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.165.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.165.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.166.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.166.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.166.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.167.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.167.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.167.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.168.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.168.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.168.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.169.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.169.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.169.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.170.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.170.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.170.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.171.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.171.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.171.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.172.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.172.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.172.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.173.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.173.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.173.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.174.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.174.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.174.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.175.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.175.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.175.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.176.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.176.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.176.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.177.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.177.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.177.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.178.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.178.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.178.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.179.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.179.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.179.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.180.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.180.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.180.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.181.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.181.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.181.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.182.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.182.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.182.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.183.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.183.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.183.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.184.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.184.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.184.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.185.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.185.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.185.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.186.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.186.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.186.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.187.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.187.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.187.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.188.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.188.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.188.down_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.189.gate_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.189.up_proj.weight": "model-00124-of-000163.safetensors", + "model.layers.47.mlp.experts.189.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.190.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.190.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.190.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.191.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.191.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.191.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.192.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.192.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.192.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.193.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.193.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.193.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.194.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.194.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.194.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.195.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.195.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.195.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.196.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.196.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.196.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.197.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.197.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.197.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.198.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.198.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.198.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.199.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.199.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.199.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.200.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.200.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.200.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.201.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.201.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.201.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.202.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.202.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.202.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.203.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.203.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.203.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.204.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.204.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.204.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.205.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.205.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.205.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.206.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.206.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.206.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.207.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.207.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.207.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.208.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.208.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.208.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.209.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.209.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.209.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.210.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.210.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.210.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.211.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.211.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.211.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.212.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.212.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.212.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.213.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.213.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.213.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.214.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.214.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.214.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.215.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.215.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.215.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.216.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.216.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.216.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.217.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.217.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.217.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.218.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.218.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.218.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.219.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.219.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.219.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.220.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.220.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.220.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.221.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.221.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.221.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.222.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.222.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.222.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.223.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.223.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.223.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.224.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.224.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.224.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.225.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.225.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.225.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.226.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.226.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.226.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.227.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.227.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.227.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.228.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.228.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.228.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.229.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.229.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.229.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.230.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.230.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.230.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.231.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.231.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.231.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.232.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.232.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.232.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.233.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.233.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.233.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.234.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.234.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.234.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.235.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.235.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.235.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.236.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.236.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.236.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.237.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.237.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.237.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.238.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.238.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.238.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.239.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.239.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.239.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.240.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.240.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.240.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.241.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.241.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.241.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.242.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.242.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.242.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.243.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.243.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.243.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.244.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.244.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.244.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.245.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.245.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.245.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.246.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.246.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.246.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.247.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.247.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.247.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.248.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.248.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.248.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.249.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.249.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.249.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.250.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.250.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.250.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.251.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.251.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.251.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.252.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.252.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.252.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.253.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.253.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.253.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.254.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.254.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.254.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.255.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.255.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.mlp.experts.255.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.47.input_layernorm.weight": "model-00125-of-000163.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.q_a_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.q_a_layernorm.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.q_b_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.kv_a_proj_with_mqa.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.kv_a_layernorm.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.kv_b_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.indexer.wq_b.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.indexer.wk.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.indexer.k_norm.weight": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.indexer.k_norm.bias": "model-00125-of-000163.safetensors", + "model.layers.48.self_attn.indexer.weights_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.gate.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.gate.e_score_correction_bias": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.shared_experts.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.shared_experts.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.shared_experts.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.0.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.0.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.0.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.1.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.1.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.1.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.2.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.2.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.2.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.3.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.3.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.3.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.4.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.4.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.4.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.5.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.5.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.5.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.6.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.6.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.6.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.7.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.7.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.7.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.8.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.8.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.8.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.9.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.9.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.9.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.10.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.10.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.10.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.11.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.11.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.11.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.12.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.12.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.12.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.13.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.13.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.13.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.14.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.14.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.14.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.15.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.15.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.15.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.16.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.16.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.16.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.17.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.17.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.17.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.18.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.18.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.18.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.19.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.19.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.19.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.20.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.20.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.20.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.21.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.21.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.21.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.22.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.22.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.22.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.23.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.23.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.23.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.24.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.24.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.24.down_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.25.gate_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.25.up_proj.weight": "model-00125-of-000163.safetensors", + "model.layers.48.mlp.experts.25.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.26.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.26.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.26.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.27.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.27.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.27.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.28.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.28.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.28.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.29.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.29.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.29.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.30.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.30.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.30.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.31.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.31.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.31.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.32.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.32.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.32.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.33.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.33.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.33.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.34.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.34.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.34.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.35.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.35.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.35.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.36.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.36.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.36.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.37.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.37.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.37.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.38.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.38.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.38.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.39.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.39.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.39.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.40.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.40.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.40.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.41.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.41.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.41.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.42.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.42.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.42.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.43.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.43.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.43.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.44.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.44.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.44.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.45.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.45.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.45.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.46.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.46.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.46.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.47.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.47.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.47.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.48.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.48.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.48.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.49.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.49.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.49.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.50.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.50.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.50.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.51.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.51.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.51.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.52.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.52.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.52.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.53.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.53.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.53.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.54.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.54.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.54.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.55.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.55.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.55.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.56.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.56.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.56.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.57.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.57.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.57.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.58.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.58.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.58.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.59.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.59.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.59.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.60.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.60.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.60.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.61.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.61.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.61.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.62.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.62.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.62.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.63.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.63.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.63.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.64.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.64.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.64.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.65.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.65.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.65.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.66.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.66.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.66.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.67.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.67.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.67.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.68.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.68.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.68.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.69.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.69.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.69.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.70.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.70.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.70.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.71.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.71.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.71.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.72.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.72.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.72.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.73.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.73.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.73.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.74.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.74.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.74.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.75.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.75.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.75.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.76.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.76.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.76.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.77.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.77.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.77.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.78.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.78.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.78.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.79.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.79.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.79.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.80.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.80.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.80.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.81.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.81.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.81.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.82.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.82.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.82.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.83.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.83.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.83.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.84.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.84.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.84.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.85.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.85.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.85.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.86.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.86.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.86.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.87.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.87.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.87.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.88.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.88.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.88.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.89.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.89.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.89.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.90.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.90.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.90.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.91.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.91.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.91.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.92.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.92.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.92.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.93.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.93.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.93.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.94.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.94.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.94.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.95.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.95.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.95.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.96.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.96.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.96.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.97.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.97.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.97.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.98.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.98.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.98.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.99.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.99.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.99.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.100.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.100.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.100.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.101.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.101.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.101.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.102.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.102.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.102.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.103.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.103.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.103.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.104.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.104.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.104.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.105.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.105.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.105.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.106.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.106.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.106.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.107.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.107.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.107.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.108.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.108.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.108.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.109.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.109.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.109.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.110.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.110.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.110.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.111.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.111.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.111.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.112.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.112.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.112.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.113.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.113.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.113.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.114.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.114.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.114.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.115.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.115.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.115.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.116.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.116.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.116.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.117.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.117.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.117.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.118.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.118.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.118.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.119.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.119.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.119.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.120.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.120.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.120.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.121.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.121.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.121.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.122.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.122.up_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.122.down_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.123.gate_proj.weight": "model-00126-of-000163.safetensors", + "model.layers.48.mlp.experts.123.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.123.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.124.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.124.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.124.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.125.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.125.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.125.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.126.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.126.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.126.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.127.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.127.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.127.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.128.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.128.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.128.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.129.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.129.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.129.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.130.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.130.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.130.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.131.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.131.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.131.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.132.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.132.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.132.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.133.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.133.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.133.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.134.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.134.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.134.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.135.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.135.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.135.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.136.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.136.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.136.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.137.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.137.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.137.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.138.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.138.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.138.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.139.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.139.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.139.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.140.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.140.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.140.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.141.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.141.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.141.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.142.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.142.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.142.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.143.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.143.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.143.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.144.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.144.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.144.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.145.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.145.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.145.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.146.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.146.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.146.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.147.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.147.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.147.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.148.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.148.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.148.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.149.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.149.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.149.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.150.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.150.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.150.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.151.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.151.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.151.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.152.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.152.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.152.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.153.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.153.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.153.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.154.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.154.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.154.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.155.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.155.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.155.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.156.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.156.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.156.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.157.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.157.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.157.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.158.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.158.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.158.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.159.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.159.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.159.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.160.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.160.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.160.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.161.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.161.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.161.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.162.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.162.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.162.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.163.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.163.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.163.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.164.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.164.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.164.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.165.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.165.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.165.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.166.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.166.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.166.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.167.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.167.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.167.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.168.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.168.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.168.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.169.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.169.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.169.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.170.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.170.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.170.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.171.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.171.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.171.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.172.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.172.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.172.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.173.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.173.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.173.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.174.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.174.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.174.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.175.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.175.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.175.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.176.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.176.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.176.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.177.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.177.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.177.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.178.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.178.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.178.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.179.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.179.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.179.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.180.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.180.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.180.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.181.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.181.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.181.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.182.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.182.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.182.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.183.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.183.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.183.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.184.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.184.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.184.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.185.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.185.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.185.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.186.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.186.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.186.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.187.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.187.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.187.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.188.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.188.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.188.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.189.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.189.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.189.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.190.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.190.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.190.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.191.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.191.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.191.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.192.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.192.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.192.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.193.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.193.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.193.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.194.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.194.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.194.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.195.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.195.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.195.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.196.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.196.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.196.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.197.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.197.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.197.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.198.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.198.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.198.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.199.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.199.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.199.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.200.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.200.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.200.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.201.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.201.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.201.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.202.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.202.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.202.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.203.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.203.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.203.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.204.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.204.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.204.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.205.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.205.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.205.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.206.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.206.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.206.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.207.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.207.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.207.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.208.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.208.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.208.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.209.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.209.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.209.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.210.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.210.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.210.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.211.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.211.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.211.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.212.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.212.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.212.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.213.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.213.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.213.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.214.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.214.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.214.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.215.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.215.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.215.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.216.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.216.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.216.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.217.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.217.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.217.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.218.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.218.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.218.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.219.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.219.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.219.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.220.gate_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.220.up_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.220.down_proj.weight": "model-00127-of-000163.safetensors", + "model.layers.48.mlp.experts.221.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.221.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.221.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.222.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.222.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.222.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.223.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.223.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.223.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.224.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.224.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.224.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.225.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.225.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.225.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.226.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.226.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.226.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.227.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.227.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.227.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.228.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.228.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.228.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.229.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.229.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.229.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.230.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.230.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.230.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.231.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.231.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.231.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.232.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.232.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.232.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.233.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.233.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.233.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.234.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.234.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.234.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.235.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.235.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.235.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.236.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.236.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.236.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.237.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.237.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.237.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.238.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.238.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.238.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.239.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.239.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.239.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.240.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.240.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.240.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.241.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.241.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.241.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.242.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.242.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.242.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.243.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.243.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.243.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.244.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.244.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.244.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.245.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.245.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.245.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.246.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.246.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.246.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.247.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.247.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.247.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.248.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.248.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.248.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.249.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.249.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.249.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.250.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.250.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.250.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.251.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.251.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.251.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.252.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.252.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.252.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.253.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.253.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.253.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.254.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.254.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.254.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.255.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.255.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.mlp.experts.255.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.48.input_layernorm.weight": "model-00128-of-000163.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.q_a_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.q_a_layernorm.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.q_b_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.kv_a_proj_with_mqa.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.kv_a_layernorm.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.kv_b_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.indexer.wq_b.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.indexer.wk.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.indexer.k_norm.weight": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.indexer.k_norm.bias": "model-00128-of-000163.safetensors", + "model.layers.49.self_attn.indexer.weights_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.gate.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.gate.e_score_correction_bias": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.shared_experts.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.shared_experts.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.shared_experts.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.0.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.0.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.0.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.1.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.1.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.1.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.2.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.2.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.2.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.3.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.3.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.3.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.4.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.4.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.4.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.5.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.5.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.5.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.6.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.6.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.6.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.7.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.7.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.7.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.8.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.8.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.8.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.9.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.9.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.9.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.10.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.10.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.10.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.11.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.11.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.11.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.12.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.12.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.12.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.13.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.13.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.13.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.14.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.14.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.14.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.15.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.15.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.15.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.16.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.16.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.16.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.17.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.17.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.17.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.18.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.18.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.18.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.19.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.19.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.19.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.20.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.20.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.20.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.21.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.21.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.21.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.22.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.22.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.22.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.23.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.23.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.23.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.24.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.24.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.24.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.25.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.25.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.25.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.26.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.26.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.26.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.27.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.27.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.27.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.28.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.28.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.28.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.29.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.29.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.29.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.30.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.30.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.30.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.31.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.31.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.31.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.32.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.32.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.32.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.33.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.33.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.33.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.34.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.34.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.34.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.35.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.35.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.35.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.36.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.36.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.36.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.37.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.37.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.37.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.38.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.38.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.38.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.39.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.39.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.39.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.40.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.40.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.40.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.41.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.41.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.41.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.42.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.42.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.42.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.43.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.43.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.43.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.44.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.44.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.44.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.45.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.45.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.45.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.46.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.46.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.46.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.47.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.47.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.47.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.48.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.48.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.48.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.49.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.49.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.49.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.50.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.50.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.50.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.51.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.51.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.51.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.52.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.52.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.52.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.53.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.53.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.53.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.54.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.54.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.54.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.55.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.55.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.55.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.56.gate_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.56.up_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.56.down_proj.weight": "model-00128-of-000163.safetensors", + "model.layers.49.mlp.experts.57.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.57.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.57.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.58.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.58.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.58.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.59.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.59.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.59.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.60.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.60.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.60.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.61.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.61.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.61.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.62.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.62.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.62.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.63.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.63.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.63.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.64.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.64.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.64.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.65.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.65.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.65.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.66.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.66.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.66.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.67.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.67.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.67.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.68.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.68.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.68.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.69.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.69.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.69.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.70.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.70.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.70.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.71.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.71.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.71.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.72.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.72.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.72.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.73.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.73.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.73.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.74.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.74.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.74.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.75.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.75.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.75.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.76.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.76.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.76.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.77.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.77.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.77.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.78.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.78.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.78.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.79.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.79.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.79.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.80.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.80.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.80.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.81.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.81.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.81.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.82.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.82.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.82.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.83.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.83.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.83.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.84.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.84.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.84.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.85.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.85.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.85.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.86.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.86.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.86.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.87.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.87.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.87.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.88.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.88.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.88.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.89.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.89.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.89.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.90.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.90.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.90.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.91.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.91.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.91.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.92.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.92.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.92.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.93.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.93.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.93.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.94.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.94.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.94.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.95.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.95.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.95.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.96.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.96.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.96.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.97.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.97.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.97.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.98.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.98.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.98.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.99.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.99.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.99.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.100.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.100.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.100.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.101.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.101.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.101.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.102.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.102.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.102.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.103.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.103.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.103.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.104.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.104.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.104.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.105.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.105.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.105.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.106.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.106.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.106.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.107.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.107.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.107.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.108.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.108.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.108.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.109.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.109.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.109.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.110.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.110.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.110.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.111.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.111.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.111.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.112.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.112.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.112.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.113.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.113.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.113.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.114.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.114.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.114.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.115.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.115.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.115.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.116.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.116.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.116.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.117.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.117.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.117.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.118.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.118.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.118.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.119.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.119.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.119.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.120.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.120.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.120.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.121.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.121.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.121.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.122.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.122.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.122.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.123.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.123.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.123.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.124.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.124.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.124.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.125.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.125.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.125.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.126.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.126.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.126.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.127.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.127.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.127.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.128.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.128.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.128.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.129.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.129.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.129.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.130.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.130.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.130.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.131.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.131.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.131.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.132.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.132.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.132.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.133.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.133.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.133.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.134.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.134.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.134.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.135.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.135.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.135.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.136.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.136.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.136.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.137.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.137.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.137.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.138.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.138.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.138.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.139.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.139.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.139.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.140.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.140.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.140.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.141.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.141.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.141.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.142.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.142.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.142.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.143.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.143.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.143.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.144.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.144.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.144.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.145.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.145.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.145.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.146.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.146.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.146.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.147.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.147.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.147.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.148.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.148.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.148.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.149.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.149.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.149.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.150.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.150.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.150.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.151.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.151.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.151.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.152.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.152.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.152.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.153.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.153.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.153.down_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.154.gate_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.154.up_proj.weight": "model-00129-of-000163.safetensors", + "model.layers.49.mlp.experts.154.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.155.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.155.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.155.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.156.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.156.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.156.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.157.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.157.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.157.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.158.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.158.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.158.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.159.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.159.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.159.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.160.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.160.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.160.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.161.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.161.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.161.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.162.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.162.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.162.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.163.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.163.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.163.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.164.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.164.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.164.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.165.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.165.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.165.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.166.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.166.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.166.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.167.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.167.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.167.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.168.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.168.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.168.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.169.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.169.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.169.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.170.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.170.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.170.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.171.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.171.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.171.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.172.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.172.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.172.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.173.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.173.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.173.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.174.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.174.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.174.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.175.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.175.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.175.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.176.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.176.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.176.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.177.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.177.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.177.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.178.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.178.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.178.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.179.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.179.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.179.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.180.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.180.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.180.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.181.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.181.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.181.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.182.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.182.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.182.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.183.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.183.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.183.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.184.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.184.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.184.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.185.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.185.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.185.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.186.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.186.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.186.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.187.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.187.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.187.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.188.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.188.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.188.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.189.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.189.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.189.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.190.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.190.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.190.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.191.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.191.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.191.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.192.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.192.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.192.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.193.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.193.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.193.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.194.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.194.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.194.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.195.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.195.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.195.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.196.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.196.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.196.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.197.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.197.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.197.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.198.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.198.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.198.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.199.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.199.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.199.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.200.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.200.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.200.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.201.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.201.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.201.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.202.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.202.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.202.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.203.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.203.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.203.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.204.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.204.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.204.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.205.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.205.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.205.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.206.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.206.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.206.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.207.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.207.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.207.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.208.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.208.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.208.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.209.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.209.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.209.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.210.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.210.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.210.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.211.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.211.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.211.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.212.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.212.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.212.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.213.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.213.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.213.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.214.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.214.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.214.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.215.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.215.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.215.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.216.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.216.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.216.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.217.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.217.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.217.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.218.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.218.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.218.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.219.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.219.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.219.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.220.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.220.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.220.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.221.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.221.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.221.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.222.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.222.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.222.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.223.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.223.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.223.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.224.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.224.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.224.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.225.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.225.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.225.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.226.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.226.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.226.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.227.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.227.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.227.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.228.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.228.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.228.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.229.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.229.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.229.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.230.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.230.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.230.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.231.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.231.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.231.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.232.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.232.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.232.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.233.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.233.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.233.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.234.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.234.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.234.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.235.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.235.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.235.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.236.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.236.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.236.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.237.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.237.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.237.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.238.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.238.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.238.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.239.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.239.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.239.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.240.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.240.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.240.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.241.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.241.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.241.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.242.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.242.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.242.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.243.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.243.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.243.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.244.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.244.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.244.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.245.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.245.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.245.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.246.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.246.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.246.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.247.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.247.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.247.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.248.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.248.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.248.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.249.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.249.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.249.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.250.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.250.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.250.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.251.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.251.up_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.251.down_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.252.gate_proj.weight": "model-00130-of-000163.safetensors", + "model.layers.49.mlp.experts.252.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.252.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.253.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.253.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.253.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.254.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.254.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.254.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.255.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.255.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.mlp.experts.255.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.49.input_layernorm.weight": "model-00131-of-000163.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.q_a_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.q_a_layernorm.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.q_b_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.kv_a_proj_with_mqa.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.kv_a_layernorm.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.kv_b_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.indexer.wq_b.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.indexer.wk.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.indexer.k_norm.weight": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.indexer.k_norm.bias": "model-00131-of-000163.safetensors", + "model.layers.50.self_attn.indexer.weights_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.gate.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.gate.e_score_correction_bias": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.shared_experts.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.shared_experts.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.shared_experts.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.0.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.0.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.0.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.1.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.1.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.1.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.2.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.2.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.2.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.3.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.3.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.3.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.4.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.4.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.4.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.5.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.5.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.5.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.6.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.6.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.6.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.7.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.7.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.7.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.8.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.8.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.8.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.9.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.9.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.9.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.10.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.10.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.10.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.11.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.11.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.11.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.12.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.12.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.12.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.13.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.13.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.13.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.14.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.14.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.14.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.15.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.15.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.15.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.16.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.16.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.16.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.17.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.17.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.17.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.18.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.18.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.18.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.19.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.19.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.19.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.20.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.20.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.20.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.21.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.21.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.21.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.22.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.22.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.22.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.23.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.23.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.23.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.24.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.24.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.24.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.25.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.25.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.25.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.26.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.26.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.26.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.27.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.27.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.27.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.28.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.28.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.28.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.29.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.29.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.29.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.30.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.30.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.30.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.31.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.31.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.31.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.32.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.32.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.32.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.33.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.33.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.33.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.34.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.34.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.34.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.35.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.35.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.35.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.36.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.36.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.36.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.37.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.37.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.37.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.38.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.38.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.38.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.39.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.39.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.39.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.40.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.40.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.40.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.41.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.41.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.41.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.42.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.42.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.42.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.43.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.43.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.43.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.44.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.44.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.44.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.45.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.45.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.45.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.46.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.46.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.46.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.47.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.47.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.47.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.48.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.48.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.48.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.49.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.49.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.49.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.50.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.50.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.50.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.51.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.51.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.51.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.52.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.52.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.52.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.53.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.53.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.53.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.54.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.54.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.54.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.55.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.55.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.55.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.56.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.56.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.56.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.57.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.57.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.57.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.58.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.58.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.58.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.59.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.59.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.59.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.60.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.60.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.60.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.61.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.61.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.61.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.62.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.62.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.62.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.63.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.63.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.63.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.64.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.64.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.64.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.65.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.65.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.65.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.66.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.66.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.66.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.67.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.67.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.67.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.68.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.68.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.68.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.69.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.69.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.69.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.70.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.70.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.70.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.71.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.71.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.71.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.72.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.72.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.72.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.73.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.73.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.73.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.74.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.74.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.74.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.75.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.75.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.75.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.76.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.76.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.76.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.77.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.77.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.77.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.78.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.78.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.78.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.79.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.79.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.79.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.80.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.80.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.80.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.81.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.81.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.81.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.82.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.82.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.82.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.83.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.83.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.83.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.84.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.84.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.84.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.85.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.85.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.85.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.86.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.86.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.86.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.87.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.87.up_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.87.down_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.88.gate_proj.weight": "model-00131-of-000163.safetensors", + "model.layers.50.mlp.experts.88.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.88.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.89.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.89.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.89.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.90.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.90.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.90.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.91.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.91.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.91.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.92.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.92.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.92.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.93.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.93.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.93.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.94.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.94.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.94.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.95.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.95.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.95.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.96.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.96.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.96.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.97.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.97.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.97.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.98.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.98.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.98.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.99.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.99.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.99.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.100.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.100.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.100.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.101.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.101.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.101.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.102.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.102.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.102.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.103.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.103.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.103.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.104.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.104.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.104.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.105.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.105.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.105.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.106.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.106.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.106.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.107.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.107.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.107.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.108.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.108.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.108.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.109.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.109.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.109.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.110.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.110.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.110.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.111.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.111.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.111.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.112.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.112.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.112.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.113.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.113.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.113.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.114.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.114.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.114.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.115.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.115.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.115.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.116.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.116.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.116.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.117.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.117.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.117.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.118.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.118.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.118.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.119.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.119.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.119.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.120.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.120.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.120.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.121.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.121.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.121.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.122.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.122.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.122.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.123.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.123.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.123.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.124.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.124.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.124.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.125.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.125.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.125.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.126.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.126.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.126.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.127.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.127.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.127.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.128.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.128.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.128.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.129.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.129.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.129.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.130.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.130.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.130.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.131.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.131.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.131.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.132.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.132.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.132.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.133.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.133.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.133.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.134.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.134.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.134.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.135.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.135.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.135.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.136.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.136.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.136.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.137.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.137.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.137.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.138.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.138.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.138.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.139.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.139.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.139.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.140.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.140.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.140.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.141.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.141.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.141.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.142.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.142.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.142.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.143.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.143.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.143.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.144.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.144.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.144.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.145.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.145.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.145.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.146.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.146.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.146.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.147.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.147.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.147.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.148.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.148.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.148.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.149.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.149.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.149.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.150.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.150.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.150.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.151.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.151.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.151.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.152.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.152.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.152.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.153.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.153.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.153.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.154.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.154.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.154.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.155.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.155.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.155.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.156.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.156.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.156.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.157.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.157.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.157.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.158.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.158.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.158.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.159.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.159.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.159.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.160.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.160.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.160.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.161.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.161.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.161.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.162.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.162.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.162.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.163.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.163.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.163.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.164.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.164.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.164.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.165.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.165.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.165.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.166.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.166.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.166.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.167.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.167.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.167.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.168.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.168.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.168.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.169.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.169.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.169.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.170.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.170.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.170.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.171.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.171.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.171.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.172.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.172.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.172.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.173.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.173.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.173.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.174.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.174.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.174.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.175.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.175.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.175.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.176.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.176.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.176.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.177.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.177.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.177.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.178.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.178.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.178.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.179.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.179.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.179.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.180.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.180.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.180.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.181.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.181.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.181.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.182.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.182.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.182.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.183.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.183.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.183.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.184.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.184.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.184.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.185.gate_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.185.up_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.185.down_proj.weight": "model-00132-of-000163.safetensors", + "model.layers.50.mlp.experts.186.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.186.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.186.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.187.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.187.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.187.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.188.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.188.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.188.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.189.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.189.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.189.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.190.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.190.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.190.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.191.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.191.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.191.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.192.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.192.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.192.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.193.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.193.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.193.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.194.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.194.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.194.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.195.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.195.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.195.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.196.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.196.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.196.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.197.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.197.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.197.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.198.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.198.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.198.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.199.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.199.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.199.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.200.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.200.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.200.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.201.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.201.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.201.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.202.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.202.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.202.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.203.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.203.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.203.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.204.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.204.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.204.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.205.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.205.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.205.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.206.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.206.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.206.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.207.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.207.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.207.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.208.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.208.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.208.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.209.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.209.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.209.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.210.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.210.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.210.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.211.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.211.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.211.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.212.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.212.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.212.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.213.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.213.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.213.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.214.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.214.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.214.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.215.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.215.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.215.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.216.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.216.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.216.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.217.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.217.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.217.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.218.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.218.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.218.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.219.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.219.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.219.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.220.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.220.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.220.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.221.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.221.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.221.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.222.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.222.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.222.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.223.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.223.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.223.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.224.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.224.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.224.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.225.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.225.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.225.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.226.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.226.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.226.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.227.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.227.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.227.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.228.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.228.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.228.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.229.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.229.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.229.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.230.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.230.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.230.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.231.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.231.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.231.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.232.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.232.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.232.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.233.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.233.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.233.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.234.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.234.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.234.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.235.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.235.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.235.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.236.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.236.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.236.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.237.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.237.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.237.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.238.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.238.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.238.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.239.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.239.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.239.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.240.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.240.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.240.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.241.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.241.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.241.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.242.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.242.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.242.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.243.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.243.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.243.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.244.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.244.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.244.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.245.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.245.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.245.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.246.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.246.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.246.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.247.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.247.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.247.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.248.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.248.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.248.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.249.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.249.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.249.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.250.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.250.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.250.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.251.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.251.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.251.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.252.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.252.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.252.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.253.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.253.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.253.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.254.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.254.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.254.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.255.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.255.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.mlp.experts.255.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.50.input_layernorm.weight": "model-00133-of-000163.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.q_a_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.q_a_layernorm.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.q_b_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.kv_a_proj_with_mqa.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.kv_a_layernorm.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.kv_b_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.indexer.wq_b.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.indexer.wk.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.indexer.k_norm.weight": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.indexer.k_norm.bias": "model-00133-of-000163.safetensors", + "model.layers.51.self_attn.indexer.weights_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.gate.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.gate.e_score_correction_bias": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.shared_experts.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.shared_experts.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.shared_experts.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.0.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.0.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.0.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.1.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.1.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.1.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.2.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.2.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.2.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.3.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.3.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.3.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.4.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.4.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.4.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.5.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.5.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.5.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.6.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.6.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.6.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.7.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.7.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.7.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.8.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.8.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.8.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.9.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.9.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.9.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.10.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.10.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.10.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.11.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.11.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.11.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.12.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.12.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.12.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.13.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.13.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.13.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.14.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.14.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.14.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.15.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.15.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.15.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.16.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.16.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.16.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.17.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.17.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.17.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.18.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.18.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.18.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.19.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.19.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.19.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.20.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.20.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.20.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.21.gate_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.21.up_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.21.down_proj.weight": "model-00133-of-000163.safetensors", + "model.layers.51.mlp.experts.22.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.22.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.22.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.23.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.23.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.23.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.24.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.24.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.24.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.25.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.25.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.25.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.26.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.26.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.26.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.27.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.27.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.27.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.28.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.28.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.28.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.29.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.29.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.29.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.30.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.30.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.30.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.31.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.31.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.31.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.32.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.32.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.32.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.33.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.33.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.33.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.34.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.34.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.34.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.35.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.35.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.35.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.36.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.36.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.36.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.37.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.37.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.37.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.38.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.38.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.38.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.39.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.39.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.39.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.40.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.40.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.40.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.41.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.41.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.41.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.42.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.42.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.42.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.43.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.43.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.43.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.44.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.44.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.44.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.45.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.45.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.45.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.46.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.46.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.46.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.47.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.47.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.47.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.48.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.48.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.48.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.49.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.49.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.49.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.50.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.50.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.50.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.51.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.51.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.51.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.52.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.52.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.52.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.53.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.53.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.53.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.54.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.54.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.54.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.55.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.55.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.55.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.56.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.56.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.56.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.57.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.57.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.57.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.58.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.58.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.58.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.59.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.59.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.59.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.60.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.60.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.60.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.61.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.61.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.61.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.62.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.62.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.62.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.63.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.63.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.63.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.64.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.64.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.64.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.65.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.65.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.65.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.66.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.66.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.66.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.67.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.67.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.67.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.68.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.68.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.68.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.69.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.69.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.69.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.70.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.70.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.70.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.71.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.71.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.71.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.72.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.72.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.72.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.73.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.73.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.73.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.74.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.74.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.74.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.75.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.75.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.75.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.76.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.76.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.76.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.77.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.77.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.77.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.78.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.78.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.78.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.79.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.79.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.79.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.80.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.80.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.80.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.81.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.81.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.81.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.82.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.82.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.82.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.83.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.83.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.83.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.84.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.84.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.84.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.85.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.85.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.85.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.86.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.86.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.86.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.87.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.87.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.87.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.88.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.88.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.88.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.89.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.89.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.89.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.90.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.90.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.90.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.91.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.91.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.91.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.92.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.92.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.92.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.93.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.93.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.93.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.94.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.94.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.94.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.95.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.95.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.95.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.96.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.96.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.96.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.97.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.97.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.97.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.98.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.98.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.98.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.99.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.99.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.99.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.100.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.100.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.100.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.101.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.101.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.101.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.102.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.102.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.102.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.103.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.103.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.103.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.104.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.104.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.104.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.105.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.105.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.105.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.106.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.106.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.106.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.107.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.107.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.107.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.108.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.108.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.108.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.109.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.109.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.109.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.110.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.110.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.110.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.111.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.111.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.111.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.112.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.112.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.112.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.113.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.113.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.113.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.114.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.114.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.114.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.115.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.115.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.115.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.116.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.116.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.116.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.117.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.117.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.117.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.118.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.118.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.118.down_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.119.gate_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.119.up_proj.weight": "model-00134-of-000163.safetensors", + "model.layers.51.mlp.experts.119.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.120.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.120.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.120.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.121.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.121.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.121.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.122.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.122.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.122.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.123.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.123.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.123.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.124.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.124.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.124.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.125.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.125.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.125.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.126.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.126.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.126.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.127.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.127.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.127.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.128.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.128.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.128.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.129.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.129.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.129.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.130.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.130.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.130.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.131.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.131.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.131.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.132.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.132.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.132.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.133.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.133.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.133.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.134.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.134.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.134.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.135.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.135.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.135.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.136.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.136.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.136.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.137.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.137.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.137.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.138.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.138.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.138.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.139.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.139.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.139.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.140.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.140.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.140.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.141.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.141.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.141.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.142.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.142.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.142.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.143.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.143.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.143.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.144.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.144.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.144.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.145.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.145.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.145.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.146.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.146.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.146.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.147.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.147.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.147.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.148.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.148.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.148.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.149.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.149.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.149.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.150.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.150.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.150.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.151.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.151.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.151.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.152.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.152.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.152.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.153.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.153.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.153.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.154.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.154.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.154.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.155.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.155.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.155.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.156.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.156.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.156.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.157.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.157.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.157.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.158.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.158.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.158.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.159.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.159.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.159.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.160.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.160.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.160.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.161.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.161.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.161.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.162.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.162.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.162.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.163.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.163.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.163.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.164.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.164.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.164.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.165.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.165.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.165.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.166.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.166.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.166.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.167.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.167.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.167.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.168.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.168.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.168.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.169.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.169.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.169.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.170.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.170.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.170.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.171.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.171.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.171.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.172.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.172.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.172.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.173.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.173.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.173.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.174.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.174.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.174.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.175.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.175.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.175.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.176.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.176.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.176.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.177.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.177.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.177.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.178.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.178.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.178.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.179.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.179.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.179.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.180.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.180.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.180.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.181.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.181.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.181.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.182.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.182.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.182.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.183.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.183.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.183.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.184.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.184.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.184.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.185.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.185.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.185.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.186.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.186.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.186.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.187.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.187.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.187.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.188.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.188.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.188.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.189.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.189.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.189.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.190.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.190.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.190.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.191.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.191.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.191.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.192.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.192.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.192.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.193.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.193.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.193.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.194.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.194.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.194.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.195.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.195.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.195.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.196.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.196.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.196.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.197.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.197.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.197.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.198.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.198.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.198.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.199.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.199.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.199.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.200.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.200.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.200.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.201.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.201.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.201.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.202.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.202.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.202.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.203.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.203.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.203.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.204.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.204.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.204.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.205.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.205.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.205.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.206.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.206.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.206.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.207.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.207.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.207.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.208.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.208.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.208.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.209.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.209.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.209.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.210.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.210.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.210.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.211.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.211.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.211.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.212.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.212.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.212.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.213.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.213.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.213.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.214.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.214.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.214.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.215.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.215.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.215.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.216.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.216.up_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.216.down_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.217.gate_proj.weight": "model-00135-of-000163.safetensors", + "model.layers.51.mlp.experts.217.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.217.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.218.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.218.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.218.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.219.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.219.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.219.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.220.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.220.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.220.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.221.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.221.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.221.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.222.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.222.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.222.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.223.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.223.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.223.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.224.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.224.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.224.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.225.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.225.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.225.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.226.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.226.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.226.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.227.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.227.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.227.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.228.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.228.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.228.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.229.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.229.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.229.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.230.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.230.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.230.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.231.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.231.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.231.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.232.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.232.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.232.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.233.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.233.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.233.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.234.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.234.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.234.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.235.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.235.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.235.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.236.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.236.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.236.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.237.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.237.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.237.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.238.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.238.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.238.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.239.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.239.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.239.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.240.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.240.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.240.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.241.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.241.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.241.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.242.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.242.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.242.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.243.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.243.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.243.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.244.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.244.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.244.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.245.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.245.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.245.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.246.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.246.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.246.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.247.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.247.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.247.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.248.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.248.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.248.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.249.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.249.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.249.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.250.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.250.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.250.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.251.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.251.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.251.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.252.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.252.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.252.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.253.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.253.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.253.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.254.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.254.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.254.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.255.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.255.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.mlp.experts.255.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.51.input_layernorm.weight": "model-00136-of-000163.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.q_a_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.q_a_layernorm.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.q_b_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.kv_a_proj_with_mqa.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.kv_a_layernorm.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.kv_b_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.indexer.wq_b.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.indexer.wk.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.indexer.k_norm.weight": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.indexer.k_norm.bias": "model-00136-of-000163.safetensors", + "model.layers.52.self_attn.indexer.weights_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.gate.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.gate.e_score_correction_bias": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.shared_experts.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.shared_experts.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.shared_experts.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.0.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.0.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.0.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.1.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.1.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.1.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.2.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.2.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.2.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.3.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.3.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.3.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.4.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.4.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.4.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.5.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.5.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.5.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.6.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.6.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.6.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.7.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.7.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.7.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.8.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.8.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.8.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.9.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.9.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.9.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.10.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.10.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.10.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.11.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.11.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.11.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.12.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.12.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.12.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.13.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.13.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.13.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.14.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.14.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.14.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.15.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.15.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.15.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.16.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.16.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.16.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.17.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.17.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.17.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.18.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.18.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.18.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.19.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.19.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.19.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.20.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.20.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.20.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.21.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.21.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.21.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.22.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.22.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.22.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.23.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.23.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.23.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.24.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.24.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.24.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.25.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.25.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.25.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.26.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.26.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.26.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.27.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.27.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.27.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.28.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.28.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.28.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.29.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.29.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.29.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.30.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.30.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.30.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.31.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.31.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.31.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.32.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.32.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.32.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.33.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.33.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.33.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.34.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.34.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.34.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.35.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.35.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.35.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.36.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.36.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.36.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.37.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.37.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.37.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.38.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.38.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.38.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.39.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.39.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.39.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.40.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.40.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.40.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.41.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.41.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.41.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.42.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.42.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.42.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.43.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.43.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.43.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.44.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.44.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.44.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.45.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.45.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.45.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.46.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.46.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.46.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.47.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.47.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.47.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.48.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.48.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.48.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.49.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.49.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.49.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.50.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.50.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.50.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.51.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.51.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.51.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.52.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.52.up_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.52.down_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.53.gate_proj.weight": "model-00136-of-000163.safetensors", + "model.layers.52.mlp.experts.53.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.53.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.54.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.54.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.54.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.55.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.55.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.55.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.56.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.56.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.56.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.57.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.57.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.57.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.58.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.58.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.58.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.59.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.59.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.59.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.60.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.60.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.60.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.61.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.61.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.61.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.62.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.62.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.62.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.63.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.63.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.63.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.64.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.64.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.64.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.65.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.65.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.65.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.66.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.66.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.66.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.67.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.67.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.67.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.68.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.68.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.68.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.69.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.69.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.69.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.70.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.70.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.70.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.71.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.71.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.71.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.72.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.72.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.72.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.73.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.73.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.73.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.74.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.74.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.74.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.75.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.75.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.75.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.76.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.76.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.76.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.77.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.77.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.77.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.78.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.78.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.78.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.79.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.79.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.79.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.80.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.80.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.80.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.81.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.81.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.81.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.82.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.82.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.82.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.83.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.83.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.83.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.84.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.84.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.84.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.85.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.85.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.85.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.86.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.86.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.86.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.87.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.87.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.87.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.88.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.88.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.88.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.89.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.89.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.89.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.90.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.90.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.90.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.91.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.91.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.91.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.92.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.92.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.92.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.93.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.93.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.93.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.94.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.94.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.94.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.95.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.95.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.95.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.96.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.96.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.96.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.97.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.97.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.97.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.98.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.98.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.98.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.99.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.99.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.99.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.100.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.100.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.100.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.101.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.101.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.101.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.102.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.102.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.102.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.103.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.103.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.103.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.104.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.104.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.104.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.105.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.105.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.105.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.106.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.106.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.106.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.107.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.107.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.107.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.108.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.108.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.108.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.109.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.109.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.109.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.110.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.110.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.110.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.111.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.111.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.111.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.112.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.112.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.112.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.113.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.113.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.113.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.114.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.114.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.114.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.115.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.115.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.115.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.116.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.116.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.116.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.117.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.117.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.117.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.118.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.118.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.118.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.119.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.119.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.119.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.120.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.120.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.120.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.121.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.121.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.121.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.122.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.122.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.122.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.123.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.123.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.123.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.124.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.124.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.124.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.125.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.125.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.125.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.126.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.126.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.126.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.127.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.127.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.127.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.128.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.128.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.128.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.129.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.129.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.129.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.130.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.130.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.130.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.131.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.131.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.131.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.132.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.132.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.132.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.133.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.133.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.133.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.134.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.134.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.134.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.135.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.135.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.135.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.136.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.136.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.136.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.137.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.137.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.137.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.138.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.138.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.138.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.139.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.139.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.139.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.140.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.140.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.140.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.141.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.141.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.141.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.142.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.142.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.142.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.143.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.143.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.143.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.144.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.144.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.144.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.145.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.145.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.145.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.146.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.146.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.146.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.147.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.147.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.147.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.148.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.148.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.148.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.149.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.149.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.149.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.150.gate_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.150.up_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.150.down_proj.weight": "model-00137-of-000163.safetensors", + "model.layers.52.mlp.experts.151.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.151.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.151.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.152.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.152.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.152.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.153.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.153.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.153.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.154.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.154.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.154.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.155.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.155.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.155.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.156.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.156.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.156.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.157.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.157.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.157.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.158.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.158.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.158.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.159.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.159.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.159.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.160.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.160.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.160.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.161.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.161.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.161.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.162.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.162.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.162.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.163.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.163.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.163.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.164.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.164.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.164.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.165.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.165.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.165.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.166.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.166.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.166.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.167.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.167.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.167.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.168.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.168.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.168.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.169.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.169.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.169.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.170.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.170.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.170.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.171.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.171.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.171.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.172.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.172.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.172.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.173.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.173.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.173.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.174.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.174.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.174.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.175.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.175.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.175.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.176.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.176.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.176.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.177.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.177.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.177.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.178.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.178.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.178.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.179.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.179.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.179.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.180.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.180.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.180.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.181.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.181.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.181.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.182.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.182.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.182.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.183.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.183.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.183.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.184.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.184.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.184.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.185.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.185.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.185.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.186.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.186.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.186.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.187.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.187.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.187.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.188.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.188.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.188.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.189.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.189.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.189.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.190.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.190.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.190.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.191.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.191.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.191.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.192.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.192.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.192.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.193.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.193.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.193.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.194.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.194.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.194.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.195.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.195.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.195.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.196.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.196.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.196.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.197.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.197.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.197.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.198.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.198.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.198.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.199.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.199.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.199.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.200.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.200.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.200.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.201.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.201.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.201.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.202.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.202.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.202.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.203.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.203.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.203.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.204.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.204.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.204.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.205.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.205.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.205.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.206.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.206.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.206.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.207.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.207.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.207.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.208.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.208.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.208.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.209.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.209.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.209.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.210.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.210.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.210.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.211.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.211.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.211.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.212.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.212.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.212.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.213.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.213.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.213.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.214.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.214.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.214.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.215.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.215.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.215.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.216.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.216.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.216.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.217.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.217.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.217.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.218.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.218.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.218.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.219.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.219.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.219.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.220.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.220.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.220.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.221.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.221.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.221.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.222.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.222.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.222.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.223.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.223.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.223.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.224.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.224.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.224.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.225.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.225.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.225.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.226.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.226.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.226.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.227.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.227.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.227.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.228.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.228.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.228.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.229.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.229.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.229.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.230.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.230.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.230.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.231.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.231.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.231.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.232.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.232.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.232.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.233.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.233.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.233.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.234.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.234.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.234.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.235.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.235.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.235.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.236.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.236.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.236.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.237.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.237.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.237.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.238.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.238.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.238.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.239.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.239.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.239.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.240.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.240.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.240.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.241.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.241.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.241.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.242.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.242.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.242.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.243.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.243.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.243.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.244.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.244.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.244.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.245.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.245.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.245.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.246.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.246.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.246.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.247.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.247.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.247.down_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.248.gate_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.248.up_proj.weight": "model-00138-of-000163.safetensors", + "model.layers.52.mlp.experts.248.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.249.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.249.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.249.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.250.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.250.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.250.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.251.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.251.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.251.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.252.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.252.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.252.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.253.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.253.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.253.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.254.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.254.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.254.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.255.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.255.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.mlp.experts.255.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.52.input_layernorm.weight": "model-00139-of-000163.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.q_a_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.q_a_layernorm.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.q_b_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.kv_a_proj_with_mqa.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.kv_a_layernorm.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.kv_b_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.indexer.wq_b.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.indexer.wk.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.indexer.k_norm.weight": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.indexer.k_norm.bias": "model-00139-of-000163.safetensors", + "model.layers.53.self_attn.indexer.weights_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.gate.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.gate.e_score_correction_bias": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.shared_experts.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.shared_experts.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.shared_experts.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.0.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.0.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.0.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.1.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.1.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.1.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.2.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.2.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.2.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.3.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.3.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.3.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.4.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.4.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.4.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.5.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.5.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.5.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.6.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.6.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.6.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.7.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.7.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.7.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.8.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.8.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.8.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.9.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.9.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.9.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.10.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.10.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.10.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.11.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.11.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.11.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.12.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.12.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.12.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.13.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.13.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.13.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.14.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.14.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.14.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.15.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.15.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.15.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.16.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.16.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.16.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.17.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.17.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.17.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.18.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.18.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.18.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.19.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.19.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.19.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.20.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.20.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.20.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.21.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.21.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.21.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.22.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.22.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.22.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.23.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.23.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.23.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.24.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.24.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.24.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.25.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.25.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.25.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.26.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.26.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.26.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.27.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.27.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.27.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.28.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.28.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.28.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.29.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.29.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.29.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.30.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.30.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.30.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.31.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.31.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.31.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.32.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.32.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.32.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.33.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.33.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.33.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.34.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.34.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.34.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.35.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.35.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.35.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.36.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.36.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.36.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.37.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.37.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.37.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.38.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.38.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.38.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.39.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.39.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.39.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.40.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.40.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.40.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.41.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.41.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.41.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.42.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.42.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.42.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.43.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.43.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.43.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.44.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.44.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.44.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.45.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.45.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.45.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.46.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.46.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.46.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.47.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.47.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.47.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.48.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.48.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.48.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.49.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.49.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.49.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.50.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.50.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.50.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.51.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.51.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.51.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.52.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.52.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.52.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.53.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.53.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.53.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.54.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.54.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.54.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.55.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.55.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.55.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.56.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.56.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.56.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.57.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.57.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.57.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.58.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.58.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.58.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.59.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.59.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.59.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.60.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.60.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.60.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.61.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.61.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.61.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.62.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.62.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.62.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.63.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.63.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.63.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.64.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.64.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.64.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.65.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.65.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.65.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.66.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.66.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.66.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.67.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.67.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.67.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.68.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.68.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.68.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.69.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.69.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.69.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.70.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.70.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.70.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.71.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.71.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.71.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.72.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.72.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.72.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.73.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.73.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.73.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.74.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.74.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.74.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.75.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.75.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.75.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.76.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.76.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.76.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.77.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.77.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.77.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.78.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.78.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.78.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.79.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.79.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.79.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.80.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.80.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.80.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.81.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.81.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.81.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.82.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.82.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.82.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.83.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.83.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.83.down_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.84.gate_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.84.up_proj.weight": "model-00139-of-000163.safetensors", + "model.layers.53.mlp.experts.84.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.85.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.85.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.85.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.86.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.86.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.86.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.87.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.87.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.87.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.88.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.88.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.88.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.89.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.89.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.89.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.90.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.90.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.90.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.91.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.91.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.91.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.92.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.92.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.92.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.93.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.93.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.93.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.94.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.94.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.94.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.95.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.95.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.95.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.96.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.96.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.96.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.97.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.97.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.97.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.98.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.98.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.98.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.99.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.99.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.99.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.100.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.100.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.100.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.101.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.101.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.101.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.102.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.102.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.102.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.103.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.103.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.103.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.104.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.104.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.104.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.105.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.105.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.105.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.106.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.106.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.106.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.107.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.107.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.107.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.108.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.108.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.108.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.109.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.109.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.109.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.110.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.110.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.110.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.111.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.111.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.111.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.112.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.112.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.112.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.113.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.113.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.113.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.114.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.114.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.114.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.115.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.115.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.115.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.116.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.116.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.116.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.117.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.117.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.117.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.118.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.118.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.118.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.119.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.119.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.119.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.120.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.120.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.120.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.121.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.121.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.121.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.122.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.122.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.122.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.123.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.123.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.123.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.124.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.124.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.124.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.125.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.125.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.125.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.126.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.126.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.126.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.127.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.127.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.127.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.128.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.128.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.128.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.129.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.129.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.129.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.130.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.130.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.130.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.131.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.131.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.131.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.132.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.132.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.132.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.133.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.133.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.133.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.134.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.134.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.134.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.135.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.135.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.135.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.136.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.136.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.136.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.137.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.137.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.137.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.138.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.138.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.138.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.139.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.139.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.139.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.140.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.140.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.140.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.141.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.141.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.141.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.142.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.142.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.142.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.143.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.143.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.143.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.144.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.144.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.144.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.145.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.145.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.145.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.146.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.146.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.146.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.147.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.147.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.147.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.148.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.148.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.148.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.149.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.149.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.149.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.150.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.150.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.150.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.151.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.151.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.151.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.152.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.152.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.152.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.153.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.153.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.153.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.154.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.154.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.154.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.155.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.155.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.155.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.156.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.156.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.156.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.157.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.157.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.157.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.158.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.158.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.158.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.159.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.159.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.159.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.160.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.160.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.160.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.161.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.161.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.161.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.162.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.162.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.162.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.163.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.163.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.163.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.164.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.164.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.164.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.165.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.165.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.165.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.166.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.166.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.166.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.167.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.167.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.167.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.168.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.168.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.168.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.169.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.169.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.169.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.170.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.170.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.170.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.171.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.171.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.171.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.172.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.172.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.172.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.173.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.173.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.173.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.174.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.174.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.174.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.175.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.175.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.175.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.176.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.176.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.176.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.177.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.177.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.177.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.178.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.178.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.178.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.179.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.179.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.179.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.180.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.180.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.180.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.181.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.181.up_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.181.down_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.182.gate_proj.weight": "model-00140-of-000163.safetensors", + "model.layers.53.mlp.experts.182.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.182.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.183.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.183.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.183.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.184.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.184.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.184.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.185.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.185.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.185.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.186.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.186.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.186.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.187.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.187.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.187.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.188.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.188.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.188.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.189.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.189.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.189.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.190.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.190.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.190.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.191.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.191.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.191.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.192.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.192.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.192.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.193.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.193.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.193.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.194.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.194.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.194.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.195.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.195.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.195.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.196.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.196.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.196.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.197.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.197.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.197.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.198.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.198.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.198.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.199.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.199.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.199.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.200.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.200.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.200.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.201.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.201.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.201.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.202.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.202.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.202.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.203.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.203.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.203.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.204.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.204.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.204.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.205.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.205.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.205.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.206.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.206.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.206.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.207.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.207.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.207.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.208.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.208.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.208.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.209.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.209.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.209.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.210.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.210.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.210.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.211.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.211.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.211.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.212.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.212.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.212.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.213.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.213.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.213.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.214.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.214.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.214.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.215.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.215.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.215.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.216.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.216.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.216.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.217.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.217.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.217.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.218.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.218.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.218.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.219.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.219.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.219.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.220.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.220.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.220.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.221.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.221.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.221.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.222.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.222.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.222.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.223.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.223.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.223.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.224.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.224.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.224.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.225.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.225.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.225.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.226.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.226.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.226.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.227.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.227.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.227.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.228.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.228.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.228.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.229.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.229.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.229.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.230.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.230.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.230.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.231.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.231.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.231.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.232.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.232.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.232.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.233.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.233.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.233.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.234.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.234.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.234.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.235.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.235.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.235.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.236.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.236.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.236.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.237.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.237.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.237.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.238.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.238.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.238.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.239.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.239.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.239.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.240.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.240.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.240.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.241.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.241.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.241.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.242.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.242.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.242.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.243.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.243.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.243.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.244.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.244.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.244.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.245.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.245.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.245.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.246.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.246.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.246.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.247.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.247.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.247.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.248.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.248.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.248.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.249.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.249.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.249.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.250.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.250.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.250.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.251.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.251.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.251.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.252.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.252.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.252.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.253.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.253.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.253.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.254.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.254.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.254.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.255.gate_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.255.up_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.mlp.experts.255.down_proj.weight": "model-00141-of-000163.safetensors", + "model.layers.53.input_layernorm.weight": "model-00141-of-000163.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00141-of-000163.safetensors", + "model.layers.54.self_attn.q_a_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.q_a_layernorm.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.q_b_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.kv_a_proj_with_mqa.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.kv_a_layernorm.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.kv_b_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.indexer.wq_b.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.indexer.wk.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.indexer.k_norm.weight": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.indexer.k_norm.bias": "model-00142-of-000163.safetensors", + "model.layers.54.self_attn.indexer.weights_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.gate.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.gate.e_score_correction_bias": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.shared_experts.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.shared_experts.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.shared_experts.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.0.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.0.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.0.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.1.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.1.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.1.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.2.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.2.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.2.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.3.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.3.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.3.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.4.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.4.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.4.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.5.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.5.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.5.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.6.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.6.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.6.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.7.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.7.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.7.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.8.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.8.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.8.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.9.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.9.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.9.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.10.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.10.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.10.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.11.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.11.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.11.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.12.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.12.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.12.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.13.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.13.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.13.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.14.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.14.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.14.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.15.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.15.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.15.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.16.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.16.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.16.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.17.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.17.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.17.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.18.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.18.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.18.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.19.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.19.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.19.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.20.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.20.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.20.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.21.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.21.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.21.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.22.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.22.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.22.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.23.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.23.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.23.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.24.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.24.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.24.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.25.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.25.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.25.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.26.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.26.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.26.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.27.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.27.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.27.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.28.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.28.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.28.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.29.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.29.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.29.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.30.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.30.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.30.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.31.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.31.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.31.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.32.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.32.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.32.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.33.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.33.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.33.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.34.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.34.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.34.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.35.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.35.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.35.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.36.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.36.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.36.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.37.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.37.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.37.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.38.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.38.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.38.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.39.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.39.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.39.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.40.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.40.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.40.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.41.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.41.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.41.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.42.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.42.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.42.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.43.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.43.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.43.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.44.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.44.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.44.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.45.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.45.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.45.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.46.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.46.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.46.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.47.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.47.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.47.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.48.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.48.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.48.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.49.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.49.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.49.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.50.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.50.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.50.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.51.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.51.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.51.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.52.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.52.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.52.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.53.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.53.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.53.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.54.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.54.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.54.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.55.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.55.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.55.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.56.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.56.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.56.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.57.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.57.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.57.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.58.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.58.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.58.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.59.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.59.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.59.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.60.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.60.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.60.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.61.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.61.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.61.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.62.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.62.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.62.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.63.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.63.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.63.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.64.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.64.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.64.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.65.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.65.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.65.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.66.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.66.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.66.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.67.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.67.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.67.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.68.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.68.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.68.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.69.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.69.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.69.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.70.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.70.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.70.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.71.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.71.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.71.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.72.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.72.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.72.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.73.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.73.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.73.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.74.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.74.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.74.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.75.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.75.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.75.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.76.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.76.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.76.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.77.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.77.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.77.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.78.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.78.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.78.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.79.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.79.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.79.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.80.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.80.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.80.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.81.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.81.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.81.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.82.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.82.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.82.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.83.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.83.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.83.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.84.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.84.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.84.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.85.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.85.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.85.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.86.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.86.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.86.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.87.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.87.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.87.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.88.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.88.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.88.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.89.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.89.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.89.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.90.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.90.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.90.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.91.gate_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.91.up_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.91.down_proj.weight": "model-00142-of-000163.safetensors", + "model.layers.54.mlp.experts.92.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.92.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.92.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.93.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.93.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.93.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.94.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.94.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.94.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.95.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.95.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.95.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.96.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.96.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.96.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.97.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.97.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.97.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.98.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.98.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.98.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.99.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.99.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.99.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.100.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.100.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.100.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.101.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.101.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.101.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.102.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.102.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.102.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.103.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.103.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.103.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.104.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.104.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.104.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.105.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.105.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.105.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.106.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.106.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.106.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.107.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.107.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.107.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.108.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.108.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.108.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.109.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.109.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.109.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.110.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.110.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.110.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.111.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.111.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.111.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.112.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.112.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.112.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.113.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.113.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.113.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.114.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.114.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.114.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.115.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.115.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.115.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.116.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.116.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.116.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.117.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.117.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.117.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.118.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.118.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.118.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.119.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.119.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.119.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.120.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.120.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.120.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.121.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.121.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.121.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.122.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.122.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.122.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.123.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.123.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.123.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.124.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.124.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.124.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.125.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.125.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.125.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.126.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.126.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.126.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.127.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.127.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.127.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.128.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.128.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.128.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.129.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.129.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.129.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.130.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.130.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.130.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.131.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.131.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.131.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.132.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.132.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.132.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.133.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.133.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.133.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.134.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.134.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.134.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.135.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.135.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.135.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.136.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.136.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.136.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.137.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.137.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.137.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.138.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.138.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.138.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.139.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.139.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.139.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.140.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.140.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.140.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.141.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.141.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.141.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.142.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.142.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.142.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.143.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.143.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.143.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.144.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.144.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.144.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.145.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.145.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.145.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.146.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.146.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.146.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.147.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.147.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.147.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.148.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.148.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.148.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.149.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.149.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.149.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.150.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.150.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.150.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.151.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.151.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.151.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.152.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.152.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.152.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.153.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.153.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.153.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.154.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.154.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.154.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.155.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.155.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.155.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.156.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.156.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.156.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.157.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.157.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.157.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.158.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.158.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.158.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.159.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.159.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.159.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.160.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.160.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.160.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.161.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.161.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.161.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.162.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.162.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.162.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.163.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.163.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.163.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.164.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.164.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.164.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.165.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.165.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.165.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.166.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.166.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.166.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.167.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.167.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.167.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.168.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.168.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.168.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.169.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.169.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.169.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.170.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.170.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.170.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.171.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.171.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.171.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.172.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.172.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.172.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.173.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.173.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.173.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.174.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.174.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.174.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.175.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.175.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.175.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.176.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.176.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.176.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.177.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.177.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.177.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.178.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.178.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.178.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.179.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.179.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.179.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.180.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.180.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.180.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.181.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.181.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.181.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.182.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.182.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.182.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.183.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.183.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.183.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.184.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.184.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.184.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.185.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.185.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.185.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.186.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.186.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.186.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.187.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.187.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.187.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.188.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.188.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.188.down_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.189.gate_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.189.up_proj.weight": "model-00143-of-000163.safetensors", + "model.layers.54.mlp.experts.189.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.190.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.190.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.190.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.191.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.191.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.191.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.192.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.192.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.192.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.193.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.193.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.193.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.194.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.194.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.194.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.195.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.195.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.195.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.196.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.196.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.196.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.197.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.197.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.197.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.198.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.198.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.198.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.199.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.199.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.199.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.200.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.200.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.200.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.201.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.201.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.201.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.202.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.202.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.202.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.203.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.203.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.203.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.204.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.204.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.204.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.205.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.205.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.205.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.206.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.206.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.206.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.207.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.207.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.207.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.208.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.208.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.208.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.209.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.209.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.209.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.210.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.210.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.210.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.211.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.211.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.211.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.212.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.212.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.212.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.213.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.213.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.213.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.214.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.214.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.214.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.215.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.215.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.215.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.216.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.216.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.216.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.217.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.217.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.217.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.218.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.218.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.218.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.219.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.219.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.219.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.220.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.220.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.220.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.221.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.221.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.221.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.222.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.222.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.222.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.223.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.223.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.223.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.224.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.224.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.224.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.225.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.225.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.225.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.226.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.226.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.226.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.227.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.227.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.227.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.228.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.228.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.228.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.229.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.229.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.229.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.230.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.230.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.230.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.231.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.231.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.231.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.232.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.232.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.232.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.233.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.233.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.233.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.234.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.234.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.234.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.235.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.235.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.235.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.236.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.236.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.236.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.237.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.237.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.237.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.238.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.238.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.238.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.239.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.239.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.239.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.240.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.240.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.240.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.241.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.241.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.241.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.242.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.242.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.242.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.243.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.243.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.243.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.244.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.244.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.244.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.245.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.245.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.245.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.246.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.246.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.246.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.247.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.247.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.247.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.248.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.248.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.248.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.249.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.249.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.249.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.250.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.250.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.250.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.251.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.251.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.251.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.252.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.252.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.252.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.253.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.253.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.253.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.254.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.254.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.254.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.255.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.255.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.mlp.experts.255.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.54.input_layernorm.weight": "model-00144-of-000163.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.q_a_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.q_a_layernorm.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.q_b_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.kv_a_proj_with_mqa.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.kv_a_layernorm.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.kv_b_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.indexer.wq_b.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.indexer.wk.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.indexer.k_norm.weight": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.indexer.k_norm.bias": "model-00144-of-000163.safetensors", + "model.layers.55.self_attn.indexer.weights_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.gate.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.gate.e_score_correction_bias": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.shared_experts.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.shared_experts.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.shared_experts.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.0.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.0.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.0.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.1.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.1.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.1.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.2.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.2.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.2.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.3.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.3.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.3.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.4.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.4.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.4.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.5.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.5.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.5.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.6.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.6.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.6.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.7.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.7.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.7.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.8.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.8.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.8.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.9.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.9.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.9.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.10.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.10.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.10.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.11.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.11.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.11.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.12.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.12.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.12.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.13.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.13.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.13.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.14.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.14.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.14.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.15.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.15.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.15.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.16.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.16.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.16.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.17.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.17.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.17.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.18.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.18.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.18.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.19.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.19.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.19.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.20.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.20.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.20.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.21.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.21.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.21.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.22.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.22.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.22.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.23.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.23.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.23.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.24.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.24.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.24.down_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.25.gate_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.25.up_proj.weight": "model-00144-of-000163.safetensors", + "model.layers.55.mlp.experts.25.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.26.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.26.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.26.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.27.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.27.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.27.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.28.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.28.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.28.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.29.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.29.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.29.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.30.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.30.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.30.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.31.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.31.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.31.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.32.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.32.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.32.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.33.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.33.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.33.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.34.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.34.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.34.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.35.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.35.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.35.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.36.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.36.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.36.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.37.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.37.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.37.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.38.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.38.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.38.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.39.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.39.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.39.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.40.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.40.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.40.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.41.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.41.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.41.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.42.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.42.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.42.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.43.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.43.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.43.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.44.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.44.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.44.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.45.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.45.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.45.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.46.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.46.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.46.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.47.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.47.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.47.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.48.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.48.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.48.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.49.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.49.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.49.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.50.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.50.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.50.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.51.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.51.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.51.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.52.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.52.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.52.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.53.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.53.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.53.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.54.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.54.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.54.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.55.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.55.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.55.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.56.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.56.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.56.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.57.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.57.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.57.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.58.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.58.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.58.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.59.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.59.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.59.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.60.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.60.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.60.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.61.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.61.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.61.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.62.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.62.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.62.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.63.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.63.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.63.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.64.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.64.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.64.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.65.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.65.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.65.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.66.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.66.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.66.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.67.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.67.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.67.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.68.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.68.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.68.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.69.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.69.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.69.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.70.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.70.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.70.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.71.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.71.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.71.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.72.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.72.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.72.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.73.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.73.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.73.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.74.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.74.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.74.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.75.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.75.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.75.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.76.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.76.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.76.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.77.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.77.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.77.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.78.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.78.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.78.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.79.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.79.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.79.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.80.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.80.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.80.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.81.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.81.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.81.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.82.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.82.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.82.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.83.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.83.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.83.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.84.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.84.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.84.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.85.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.85.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.85.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.86.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.86.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.86.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.87.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.87.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.87.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.88.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.88.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.88.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.89.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.89.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.89.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.90.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.90.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.90.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.91.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.91.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.91.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.92.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.92.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.92.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.93.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.93.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.93.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.94.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.94.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.94.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.95.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.95.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.95.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.96.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.96.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.96.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.97.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.97.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.97.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.98.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.98.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.98.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.99.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.99.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.99.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.100.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.100.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.100.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.101.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.101.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.101.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.102.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.102.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.102.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.103.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.103.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.103.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.104.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.104.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.104.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.105.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.105.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.105.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.106.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.106.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.106.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.107.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.107.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.107.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.108.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.108.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.108.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.109.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.109.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.109.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.110.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.110.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.110.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.111.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.111.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.111.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.112.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.112.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.112.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.113.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.113.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.113.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.114.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.114.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.114.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.115.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.115.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.115.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.116.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.116.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.116.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.117.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.117.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.117.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.118.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.118.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.118.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.119.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.119.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.119.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.120.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.120.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.120.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.121.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.121.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.121.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.122.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.122.up_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.122.down_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.123.gate_proj.weight": "model-00145-of-000163.safetensors", + "model.layers.55.mlp.experts.123.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.123.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.124.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.124.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.124.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.125.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.125.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.125.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.126.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.126.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.126.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.127.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.127.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.127.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.128.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.128.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.128.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.129.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.129.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.129.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.130.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.130.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.130.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.131.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.131.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.131.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.132.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.132.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.132.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.133.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.133.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.133.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.134.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.134.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.134.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.135.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.135.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.135.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.136.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.136.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.136.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.137.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.137.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.137.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.138.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.138.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.138.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.139.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.139.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.139.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.140.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.140.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.140.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.141.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.141.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.141.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.142.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.142.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.142.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.143.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.143.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.143.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.144.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.144.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.144.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.145.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.145.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.145.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.146.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.146.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.146.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.147.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.147.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.147.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.148.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.148.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.148.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.149.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.149.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.149.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.150.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.150.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.150.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.151.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.151.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.151.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.152.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.152.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.152.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.153.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.153.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.153.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.154.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.154.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.154.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.155.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.155.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.155.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.156.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.156.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.156.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.157.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.157.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.157.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.158.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.158.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.158.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.159.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.159.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.159.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.160.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.160.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.160.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.161.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.161.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.161.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.162.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.162.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.162.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.163.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.163.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.163.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.164.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.164.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.164.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.165.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.165.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.165.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.166.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.166.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.166.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.167.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.167.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.167.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.168.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.168.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.168.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.169.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.169.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.169.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.170.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.170.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.170.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.171.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.171.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.171.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.172.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.172.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.172.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.173.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.173.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.173.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.174.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.174.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.174.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.175.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.175.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.175.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.176.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.176.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.176.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.177.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.177.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.177.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.178.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.178.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.178.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.179.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.179.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.179.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.180.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.180.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.180.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.181.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.181.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.181.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.182.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.182.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.182.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.183.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.183.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.183.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.184.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.184.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.184.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.185.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.185.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.185.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.186.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.186.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.186.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.187.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.187.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.187.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.188.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.188.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.188.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.189.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.189.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.189.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.190.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.190.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.190.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.191.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.191.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.191.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.192.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.192.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.192.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.193.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.193.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.193.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.194.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.194.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.194.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.195.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.195.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.195.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.196.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.196.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.196.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.197.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.197.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.197.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.198.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.198.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.198.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.199.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.199.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.199.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.200.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.200.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.200.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.201.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.201.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.201.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.202.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.202.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.202.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.203.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.203.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.203.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.204.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.204.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.204.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.205.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.205.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.205.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.206.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.206.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.206.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.207.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.207.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.207.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.208.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.208.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.208.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.209.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.209.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.209.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.210.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.210.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.210.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.211.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.211.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.211.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.212.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.212.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.212.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.213.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.213.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.213.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.214.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.214.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.214.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.215.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.215.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.215.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.216.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.216.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.216.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.217.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.217.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.217.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.218.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.218.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.218.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.219.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.219.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.219.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.220.gate_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.220.up_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.220.down_proj.weight": "model-00146-of-000163.safetensors", + "model.layers.55.mlp.experts.221.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.221.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.221.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.222.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.222.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.222.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.223.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.223.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.223.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.224.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.224.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.224.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.225.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.225.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.225.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.226.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.226.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.226.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.227.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.227.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.227.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.228.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.228.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.228.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.229.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.229.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.229.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.230.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.230.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.230.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.231.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.231.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.231.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.232.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.232.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.232.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.233.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.233.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.233.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.234.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.234.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.234.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.235.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.235.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.235.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.236.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.236.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.236.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.237.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.237.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.237.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.238.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.238.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.238.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.239.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.239.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.239.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.240.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.240.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.240.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.241.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.241.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.241.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.242.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.242.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.242.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.243.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.243.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.243.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.244.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.244.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.244.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.245.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.245.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.245.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.246.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.246.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.246.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.247.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.247.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.247.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.248.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.248.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.248.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.249.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.249.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.249.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.250.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.250.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.250.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.251.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.251.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.251.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.252.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.252.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.252.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.253.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.253.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.253.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.254.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.254.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.254.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.255.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.255.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.mlp.experts.255.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.55.input_layernorm.weight": "model-00147-of-000163.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.q_a_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.q_a_layernorm.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.q_b_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.kv_a_proj_with_mqa.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.kv_a_layernorm.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.kv_b_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.indexer.wq_b.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.indexer.wk.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.indexer.k_norm.weight": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.indexer.k_norm.bias": "model-00147-of-000163.safetensors", + "model.layers.56.self_attn.indexer.weights_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.gate.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.gate.e_score_correction_bias": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.shared_experts.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.shared_experts.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.shared_experts.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.0.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.0.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.0.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.1.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.1.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.1.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.2.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.2.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.2.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.3.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.3.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.3.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.4.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.4.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.4.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.5.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.5.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.5.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.6.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.6.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.6.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.7.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.7.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.7.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.8.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.8.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.8.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.9.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.9.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.9.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.10.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.10.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.10.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.11.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.11.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.11.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.12.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.12.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.12.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.13.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.13.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.13.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.14.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.14.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.14.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.15.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.15.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.15.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.16.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.16.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.16.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.17.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.17.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.17.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.18.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.18.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.18.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.19.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.19.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.19.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.20.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.20.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.20.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.21.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.21.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.21.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.22.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.22.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.22.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.23.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.23.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.23.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.24.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.24.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.24.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.25.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.25.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.25.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.26.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.26.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.26.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.27.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.27.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.27.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.28.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.28.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.28.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.29.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.29.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.29.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.30.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.30.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.30.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.31.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.31.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.31.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.32.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.32.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.32.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.33.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.33.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.33.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.34.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.34.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.34.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.35.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.35.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.35.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.36.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.36.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.36.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.37.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.37.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.37.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.38.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.38.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.38.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.39.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.39.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.39.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.40.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.40.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.40.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.41.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.41.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.41.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.42.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.42.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.42.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.43.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.43.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.43.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.44.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.44.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.44.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.45.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.45.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.45.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.46.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.46.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.46.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.47.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.47.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.47.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.48.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.48.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.48.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.49.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.49.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.49.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.50.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.50.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.50.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.51.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.51.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.51.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.52.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.52.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.52.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.53.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.53.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.53.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.54.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.54.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.54.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.55.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.55.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.55.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.56.gate_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.56.up_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.56.down_proj.weight": "model-00147-of-000163.safetensors", + "model.layers.56.mlp.experts.57.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.57.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.57.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.58.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.58.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.58.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.59.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.59.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.59.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.60.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.60.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.60.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.61.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.61.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.61.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.62.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.62.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.62.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.63.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.63.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.63.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.64.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.64.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.64.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.65.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.65.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.65.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.66.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.66.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.66.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.67.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.67.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.67.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.68.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.68.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.68.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.69.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.69.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.69.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.70.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.70.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.70.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.71.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.71.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.71.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.72.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.72.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.72.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.73.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.73.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.73.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.74.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.74.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.74.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.75.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.75.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.75.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.76.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.76.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.76.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.77.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.77.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.77.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.78.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.78.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.78.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.79.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.79.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.79.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.80.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.80.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.80.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.81.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.81.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.81.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.82.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.82.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.82.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.83.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.83.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.83.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.84.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.84.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.84.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.85.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.85.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.85.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.86.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.86.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.86.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.87.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.87.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.87.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.88.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.88.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.88.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.89.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.89.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.89.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.90.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.90.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.90.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.91.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.91.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.91.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.92.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.92.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.92.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.93.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.93.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.93.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.94.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.94.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.94.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.95.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.95.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.95.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.96.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.96.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.96.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.97.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.97.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.97.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.98.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.98.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.98.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.99.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.99.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.99.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.100.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.100.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.100.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.101.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.101.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.101.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.102.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.102.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.102.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.103.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.103.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.103.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.104.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.104.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.104.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.105.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.105.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.105.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.106.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.106.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.106.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.107.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.107.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.107.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.108.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.108.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.108.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.109.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.109.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.109.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.110.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.110.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.110.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.111.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.111.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.111.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.112.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.112.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.112.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.113.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.113.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.113.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.114.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.114.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.114.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.115.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.115.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.115.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.116.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.116.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.116.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.117.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.117.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.117.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.118.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.118.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.118.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.119.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.119.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.119.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.120.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.120.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.120.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.121.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.121.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.121.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.122.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.122.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.122.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.123.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.123.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.123.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.124.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.124.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.124.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.125.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.125.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.125.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.126.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.126.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.126.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.127.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.127.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.127.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.128.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.128.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.128.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.129.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.129.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.129.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.130.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.130.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.130.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.131.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.131.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.131.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.132.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.132.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.132.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.133.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.133.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.133.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.134.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.134.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.134.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.135.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.135.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.135.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.136.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.136.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.136.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.137.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.137.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.137.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.138.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.138.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.138.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.139.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.139.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.139.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.140.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.140.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.140.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.141.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.141.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.141.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.142.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.142.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.142.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.143.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.143.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.143.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.144.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.144.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.144.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.145.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.145.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.145.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.146.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.146.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.146.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.147.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.147.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.147.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.148.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.148.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.148.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.149.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.149.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.149.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.150.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.150.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.150.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.151.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.151.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.151.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.152.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.152.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.152.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.153.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.153.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.153.down_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.154.gate_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.154.up_proj.weight": "model-00148-of-000163.safetensors", + "model.layers.56.mlp.experts.154.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.155.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.155.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.155.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.156.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.156.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.156.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.157.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.157.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.157.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.158.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.158.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.158.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.159.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.159.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.159.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.160.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.160.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.160.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.161.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.161.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.161.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.162.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.162.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.162.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.163.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.163.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.163.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.164.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.164.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.164.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.165.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.165.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.165.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.166.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.166.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.166.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.167.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.167.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.167.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.168.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.168.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.168.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.169.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.169.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.169.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.170.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.170.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.170.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.171.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.171.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.171.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.172.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.172.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.172.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.173.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.173.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.173.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.174.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.174.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.174.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.175.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.175.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.175.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.176.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.176.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.176.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.177.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.177.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.177.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.178.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.178.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.178.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.179.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.179.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.179.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.180.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.180.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.180.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.181.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.181.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.181.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.182.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.182.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.182.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.183.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.183.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.183.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.184.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.184.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.184.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.185.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.185.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.185.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.186.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.186.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.186.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.187.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.187.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.187.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.188.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.188.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.188.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.189.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.189.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.189.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.190.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.190.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.190.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.191.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.191.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.191.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.192.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.192.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.192.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.193.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.193.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.193.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.194.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.194.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.194.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.195.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.195.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.195.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.196.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.196.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.196.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.197.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.197.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.197.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.198.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.198.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.198.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.199.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.199.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.199.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.200.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.200.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.200.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.201.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.201.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.201.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.202.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.202.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.202.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.203.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.203.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.203.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.204.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.204.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.204.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.205.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.205.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.205.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.206.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.206.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.206.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.207.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.207.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.207.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.208.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.208.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.208.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.209.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.209.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.209.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.210.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.210.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.210.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.211.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.211.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.211.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.212.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.212.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.212.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.213.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.213.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.213.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.214.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.214.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.214.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.215.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.215.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.215.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.216.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.216.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.216.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.217.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.217.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.217.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.218.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.218.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.218.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.219.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.219.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.219.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.220.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.220.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.220.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.221.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.221.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.221.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.222.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.222.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.222.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.223.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.223.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.223.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.224.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.224.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.224.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.225.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.225.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.225.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.226.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.226.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.226.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.227.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.227.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.227.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.228.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.228.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.228.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.229.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.229.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.229.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.230.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.230.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.230.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.231.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.231.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.231.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.232.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.232.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.232.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.233.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.233.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.233.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.234.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.234.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.234.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.235.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.235.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.235.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.236.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.236.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.236.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.237.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.237.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.237.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.238.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.238.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.238.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.239.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.239.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.239.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.240.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.240.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.240.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.241.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.241.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.241.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.242.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.242.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.242.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.243.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.243.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.243.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.244.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.244.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.244.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.245.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.245.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.245.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.246.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.246.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.246.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.247.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.247.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.247.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.248.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.248.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.248.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.249.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.249.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.249.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.250.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.250.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.250.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.251.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.251.up_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.251.down_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.252.gate_proj.weight": "model-00149-of-000163.safetensors", + "model.layers.56.mlp.experts.252.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.252.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.253.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.253.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.253.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.254.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.254.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.254.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.255.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.255.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.mlp.experts.255.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.56.input_layernorm.weight": "model-00150-of-000163.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.q_a_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.q_a_layernorm.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.q_b_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.kv_a_proj_with_mqa.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.kv_a_layernorm.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.kv_b_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.indexer.wq_b.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.indexer.wk.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.indexer.k_norm.weight": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.indexer.k_norm.bias": "model-00150-of-000163.safetensors", + "model.layers.57.self_attn.indexer.weights_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.gate.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.gate.e_score_correction_bias": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.shared_experts.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.shared_experts.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.shared_experts.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.0.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.0.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.0.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.1.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.1.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.1.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.2.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.2.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.2.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.3.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.3.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.3.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.4.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.4.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.4.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.5.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.5.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.5.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.6.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.6.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.6.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.7.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.7.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.7.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.8.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.8.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.8.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.9.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.9.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.9.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.10.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.10.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.10.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.11.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.11.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.11.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.12.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.12.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.12.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.13.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.13.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.13.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.14.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.14.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.14.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.15.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.15.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.15.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.16.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.16.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.16.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.17.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.17.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.17.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.18.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.18.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.18.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.19.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.19.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.19.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.20.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.20.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.20.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.21.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.21.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.21.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.22.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.22.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.22.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.23.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.23.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.23.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.24.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.24.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.24.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.25.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.25.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.25.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.26.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.26.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.26.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.27.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.27.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.27.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.28.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.28.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.28.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.29.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.29.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.29.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.30.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.30.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.30.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.31.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.31.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.31.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.32.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.32.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.32.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.33.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.33.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.33.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.34.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.34.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.34.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.35.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.35.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.35.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.36.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.36.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.36.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.37.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.37.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.37.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.38.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.38.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.38.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.39.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.39.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.39.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.40.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.40.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.40.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.41.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.41.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.41.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.42.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.42.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.42.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.43.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.43.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.43.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.44.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.44.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.44.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.45.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.45.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.45.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.46.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.46.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.46.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.47.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.47.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.47.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.48.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.48.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.48.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.49.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.49.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.49.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.50.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.50.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.50.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.51.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.51.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.51.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.52.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.52.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.52.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.53.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.53.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.53.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.54.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.54.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.54.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.55.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.55.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.55.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.56.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.56.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.56.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.57.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.57.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.57.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.58.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.58.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.58.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.59.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.59.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.59.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.60.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.60.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.60.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.61.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.61.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.61.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.62.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.62.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.62.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.63.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.63.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.63.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.64.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.64.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.64.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.65.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.65.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.65.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.66.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.66.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.66.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.67.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.67.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.67.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.68.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.68.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.68.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.69.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.69.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.69.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.70.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.70.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.70.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.71.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.71.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.71.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.72.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.72.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.72.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.73.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.73.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.73.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.74.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.74.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.74.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.75.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.75.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.75.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.76.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.76.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.76.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.77.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.77.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.77.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.78.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.78.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.78.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.79.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.79.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.79.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.80.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.80.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.80.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.81.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.81.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.81.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.82.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.82.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.82.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.83.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.83.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.83.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.84.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.84.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.84.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.85.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.85.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.85.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.86.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.86.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.86.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.87.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.87.up_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.87.down_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.88.gate_proj.weight": "model-00150-of-000163.safetensors", + "model.layers.57.mlp.experts.88.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.88.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.89.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.89.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.89.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.90.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.90.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.90.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.91.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.91.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.91.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.92.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.92.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.92.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.93.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.93.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.93.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.94.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.94.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.94.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.95.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.95.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.95.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.96.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.96.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.96.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.97.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.97.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.97.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.98.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.98.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.98.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.99.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.99.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.99.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.100.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.100.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.100.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.101.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.101.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.101.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.102.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.102.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.102.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.103.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.103.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.103.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.104.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.104.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.104.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.105.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.105.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.105.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.106.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.106.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.106.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.107.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.107.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.107.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.108.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.108.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.108.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.109.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.109.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.109.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.110.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.110.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.110.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.111.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.111.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.111.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.112.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.112.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.112.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.113.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.113.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.113.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.114.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.114.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.114.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.115.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.115.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.115.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.116.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.116.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.116.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.117.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.117.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.117.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.118.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.118.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.118.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.119.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.119.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.119.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.120.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.120.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.120.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.121.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.121.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.121.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.122.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.122.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.122.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.123.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.123.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.123.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.124.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.124.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.124.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.125.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.125.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.125.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.126.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.126.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.126.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.127.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.127.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.127.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.128.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.128.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.128.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.129.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.129.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.129.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.130.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.130.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.130.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.131.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.131.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.131.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.132.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.132.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.132.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.133.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.133.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.133.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.134.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.134.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.134.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.135.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.135.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.135.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.136.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.136.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.136.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.137.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.137.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.137.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.138.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.138.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.138.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.139.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.139.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.139.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.140.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.140.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.140.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.141.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.141.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.141.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.142.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.142.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.142.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.143.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.143.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.143.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.144.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.144.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.144.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.145.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.145.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.145.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.146.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.146.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.146.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.147.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.147.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.147.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.148.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.148.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.148.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.149.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.149.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.149.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.150.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.150.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.150.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.151.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.151.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.151.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.152.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.152.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.152.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.153.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.153.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.153.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.154.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.154.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.154.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.155.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.155.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.155.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.156.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.156.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.156.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.157.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.157.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.157.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.158.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.158.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.158.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.159.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.159.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.159.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.160.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.160.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.160.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.161.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.161.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.161.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.162.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.162.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.162.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.163.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.163.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.163.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.164.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.164.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.164.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.165.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.165.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.165.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.166.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.166.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.166.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.167.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.167.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.167.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.168.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.168.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.168.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.169.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.169.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.169.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.170.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.170.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.170.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.171.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.171.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.171.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.172.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.172.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.172.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.173.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.173.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.173.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.174.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.174.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.174.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.175.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.175.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.175.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.176.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.176.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.176.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.177.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.177.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.177.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.178.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.178.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.178.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.179.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.179.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.179.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.180.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.180.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.180.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.181.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.181.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.181.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.182.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.182.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.182.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.183.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.183.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.183.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.184.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.184.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.184.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.185.gate_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.185.up_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.185.down_proj.weight": "model-00151-of-000163.safetensors", + "model.layers.57.mlp.experts.186.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.186.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.186.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.187.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.187.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.187.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.188.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.188.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.188.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.189.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.189.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.189.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.190.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.190.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.190.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.191.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.191.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.191.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.192.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.192.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.192.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.193.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.193.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.193.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.194.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.194.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.194.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.195.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.195.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.195.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.196.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.196.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.196.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.197.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.197.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.197.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.198.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.198.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.198.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.199.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.199.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.199.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.200.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.200.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.200.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.201.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.201.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.201.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.202.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.202.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.202.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.203.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.203.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.203.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.204.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.204.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.204.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.205.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.205.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.205.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.206.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.206.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.206.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.207.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.207.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.207.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.208.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.208.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.208.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.209.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.209.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.209.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.210.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.210.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.210.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.211.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.211.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.211.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.212.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.212.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.212.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.213.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.213.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.213.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.214.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.214.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.214.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.215.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.215.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.215.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.216.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.216.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.216.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.217.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.217.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.217.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.218.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.218.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.218.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.219.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.219.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.219.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.220.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.220.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.220.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.221.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.221.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.221.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.222.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.222.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.222.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.223.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.223.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.223.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.224.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.224.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.224.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.225.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.225.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.225.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.226.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.226.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.226.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.227.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.227.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.227.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.228.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.228.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.228.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.229.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.229.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.229.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.230.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.230.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.230.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.231.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.231.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.231.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.232.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.232.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.232.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.233.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.233.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.233.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.234.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.234.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.234.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.235.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.235.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.235.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.236.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.236.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.236.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.237.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.237.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.237.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.238.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.238.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.238.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.239.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.239.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.239.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.240.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.240.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.240.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.241.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.241.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.241.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.242.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.242.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.242.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.243.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.243.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.243.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.244.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.244.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.244.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.245.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.245.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.245.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.246.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.246.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.246.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.247.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.247.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.247.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.248.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.248.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.248.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.249.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.249.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.249.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.250.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.250.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.250.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.251.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.251.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.251.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.252.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.252.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.252.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.253.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.253.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.253.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.254.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.254.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.254.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.255.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.255.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.mlp.experts.255.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.57.input_layernorm.weight": "model-00152-of-000163.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.q_a_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.q_a_layernorm.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.q_b_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.kv_a_proj_with_mqa.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.kv_a_layernorm.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.kv_b_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.indexer.wq_b.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.indexer.wk.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.indexer.k_norm.weight": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.indexer.k_norm.bias": "model-00152-of-000163.safetensors", + "model.layers.58.self_attn.indexer.weights_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.gate.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.gate.e_score_correction_bias": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.shared_experts.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.shared_experts.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.shared_experts.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.0.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.0.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.0.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.1.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.1.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.1.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.2.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.2.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.2.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.3.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.3.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.3.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.4.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.4.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.4.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.5.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.5.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.5.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.6.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.6.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.6.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.7.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.7.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.7.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.8.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.8.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.8.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.9.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.9.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.9.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.10.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.10.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.10.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.11.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.11.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.11.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.12.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.12.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.12.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.13.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.13.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.13.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.14.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.14.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.14.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.15.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.15.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.15.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.16.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.16.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.16.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.17.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.17.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.17.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.18.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.18.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.18.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.19.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.19.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.19.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.20.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.20.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.20.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.21.gate_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.21.up_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.21.down_proj.weight": "model-00152-of-000163.safetensors", + "model.layers.58.mlp.experts.22.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.22.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.22.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.23.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.23.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.23.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.24.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.24.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.24.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.25.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.25.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.25.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.26.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.26.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.26.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.27.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.27.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.27.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.28.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.28.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.28.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.29.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.29.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.29.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.30.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.30.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.30.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.31.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.31.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.31.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.32.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.32.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.32.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.33.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.33.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.33.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.34.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.34.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.34.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.35.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.35.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.35.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.36.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.36.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.36.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.37.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.37.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.37.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.38.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.38.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.38.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.39.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.39.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.39.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.40.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.40.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.40.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.41.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.41.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.41.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.42.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.42.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.42.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.43.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.43.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.43.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.44.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.44.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.44.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.45.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.45.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.45.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.46.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.46.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.46.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.47.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.47.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.47.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.48.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.48.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.48.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.49.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.49.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.49.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.50.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.50.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.50.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.51.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.51.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.51.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.52.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.52.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.52.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.53.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.53.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.53.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.54.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.54.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.54.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.55.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.55.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.55.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.56.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.56.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.56.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.57.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.57.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.57.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.58.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.58.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.58.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.59.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.59.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.59.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.60.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.60.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.60.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.61.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.61.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.61.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.62.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.62.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.62.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.63.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.63.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.63.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.64.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.64.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.64.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.65.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.65.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.65.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.66.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.66.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.66.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.67.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.67.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.67.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.68.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.68.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.68.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.69.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.69.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.69.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.70.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.70.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.70.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.71.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.71.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.71.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.72.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.72.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.72.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.73.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.73.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.73.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.74.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.74.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.74.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.75.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.75.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.75.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.76.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.76.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.76.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.77.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.77.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.77.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.78.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.78.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.78.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.79.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.79.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.79.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.80.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.80.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.80.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.81.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.81.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.81.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.82.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.82.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.82.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.83.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.83.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.83.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.84.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.84.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.84.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.85.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.85.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.85.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.86.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.86.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.86.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.87.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.87.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.87.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.88.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.88.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.88.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.89.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.89.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.89.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.90.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.90.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.90.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.91.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.91.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.91.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.92.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.92.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.92.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.93.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.93.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.93.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.94.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.94.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.94.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.95.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.95.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.95.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.96.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.96.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.96.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.97.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.97.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.97.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.98.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.98.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.98.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.99.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.99.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.99.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.100.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.100.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.100.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.101.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.101.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.101.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.102.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.102.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.102.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.103.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.103.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.103.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.104.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.104.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.104.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.105.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.105.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.105.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.106.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.106.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.106.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.107.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.107.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.107.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.108.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.108.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.108.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.109.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.109.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.109.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.110.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.110.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.110.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.111.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.111.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.111.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.112.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.112.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.112.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.113.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.113.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.113.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.114.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.114.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.114.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.115.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.115.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.115.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.116.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.116.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.116.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.117.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.117.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.117.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.118.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.118.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.118.down_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.119.gate_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.119.up_proj.weight": "model-00153-of-000163.safetensors", + "model.layers.58.mlp.experts.119.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.120.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.120.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.120.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.121.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.121.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.121.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.122.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.122.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.122.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.123.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.123.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.123.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.124.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.124.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.124.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.125.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.125.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.125.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.126.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.126.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.126.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.127.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.127.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.127.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.128.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.128.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.128.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.129.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.129.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.129.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.130.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.130.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.130.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.131.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.131.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.131.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.132.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.132.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.132.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.133.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.133.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.133.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.134.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.134.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.134.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.135.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.135.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.135.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.136.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.136.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.136.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.137.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.137.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.137.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.138.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.138.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.138.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.139.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.139.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.139.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.140.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.140.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.140.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.141.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.141.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.141.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.142.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.142.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.142.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.143.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.143.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.143.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.144.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.144.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.144.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.145.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.145.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.145.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.146.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.146.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.146.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.147.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.147.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.147.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.148.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.148.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.148.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.149.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.149.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.149.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.150.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.150.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.150.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.151.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.151.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.151.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.152.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.152.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.152.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.153.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.153.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.153.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.154.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.154.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.154.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.155.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.155.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.155.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.156.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.156.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.156.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.157.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.157.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.157.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.158.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.158.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.158.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.159.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.159.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.159.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.160.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.160.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.160.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.161.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.161.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.161.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.162.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.162.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.162.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.163.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.163.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.163.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.164.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.164.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.164.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.165.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.165.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.165.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.166.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.166.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.166.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.167.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.167.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.167.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.168.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.168.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.168.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.169.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.169.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.169.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.170.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.170.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.170.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.171.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.171.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.171.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.172.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.172.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.172.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.173.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.173.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.173.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.174.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.174.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.174.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.175.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.175.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.175.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.176.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.176.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.176.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.177.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.177.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.177.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.178.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.178.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.178.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.179.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.179.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.179.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.180.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.180.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.180.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.181.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.181.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.181.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.182.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.182.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.182.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.183.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.183.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.183.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.184.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.184.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.184.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.185.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.185.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.185.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.186.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.186.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.186.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.187.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.187.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.187.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.188.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.188.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.188.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.189.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.189.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.189.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.190.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.190.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.190.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.191.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.191.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.191.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.192.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.192.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.192.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.193.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.193.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.193.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.194.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.194.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.194.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.195.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.195.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.195.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.196.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.196.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.196.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.197.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.197.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.197.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.198.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.198.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.198.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.199.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.199.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.199.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.200.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.200.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.200.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.201.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.201.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.201.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.202.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.202.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.202.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.203.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.203.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.203.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.204.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.204.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.204.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.205.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.205.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.205.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.206.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.206.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.206.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.207.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.207.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.207.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.208.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.208.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.208.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.209.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.209.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.209.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.210.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.210.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.210.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.211.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.211.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.211.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.212.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.212.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.212.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.213.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.213.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.213.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.214.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.214.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.214.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.215.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.215.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.215.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.216.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.216.up_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.216.down_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.217.gate_proj.weight": "model-00154-of-000163.safetensors", + "model.layers.58.mlp.experts.217.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.217.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.218.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.218.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.218.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.219.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.219.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.219.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.220.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.220.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.220.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.221.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.221.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.221.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.222.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.222.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.222.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.223.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.223.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.223.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.224.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.224.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.224.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.225.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.225.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.225.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.226.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.226.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.226.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.227.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.227.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.227.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.228.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.228.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.228.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.229.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.229.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.229.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.230.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.230.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.230.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.231.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.231.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.231.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.232.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.232.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.232.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.233.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.233.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.233.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.234.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.234.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.234.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.235.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.235.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.235.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.236.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.236.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.236.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.237.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.237.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.237.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.238.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.238.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.238.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.239.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.239.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.239.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.240.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.240.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.240.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.241.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.241.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.241.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.242.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.242.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.242.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.243.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.243.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.243.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.244.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.244.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.244.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.245.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.245.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.245.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.246.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.246.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.246.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.247.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.247.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.247.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.248.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.248.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.248.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.249.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.249.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.249.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.250.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.250.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.250.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.251.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.251.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.251.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.252.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.252.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.252.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.253.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.253.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.253.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.254.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.254.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.254.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.255.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.255.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.mlp.experts.255.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.58.input_layernorm.weight": "model-00155-of-000163.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.q_a_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.q_a_layernorm.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.q_b_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.kv_a_proj_with_mqa.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.kv_a_layernorm.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.kv_b_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.indexer.wq_b.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.indexer.wk.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.indexer.k_norm.weight": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.indexer.k_norm.bias": "model-00155-of-000163.safetensors", + "model.layers.59.self_attn.indexer.weights_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.gate.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.gate.e_score_correction_bias": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.shared_experts.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.shared_experts.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.shared_experts.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.0.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.0.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.0.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.1.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.1.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.1.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.2.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.2.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.2.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.3.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.3.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.3.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.4.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.4.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.4.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.5.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.5.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.5.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.6.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.6.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.6.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.7.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.7.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.7.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.8.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.8.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.8.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.9.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.9.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.9.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.10.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.10.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.10.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.11.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.11.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.11.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.12.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.12.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.12.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.13.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.13.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.13.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.14.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.14.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.14.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.15.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.15.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.15.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.16.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.16.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.16.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.17.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.17.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.17.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.18.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.18.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.18.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.19.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.19.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.19.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.20.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.20.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.20.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.21.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.21.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.21.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.22.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.22.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.22.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.23.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.23.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.23.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.24.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.24.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.24.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.25.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.25.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.25.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.26.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.26.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.26.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.27.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.27.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.27.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.28.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.28.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.28.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.29.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.29.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.29.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.30.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.30.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.30.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.31.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.31.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.31.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.32.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.32.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.32.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.33.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.33.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.33.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.34.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.34.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.34.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.35.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.35.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.35.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.36.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.36.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.36.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.37.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.37.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.37.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.38.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.38.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.38.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.39.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.39.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.39.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.40.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.40.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.40.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.41.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.41.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.41.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.42.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.42.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.42.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.43.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.43.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.43.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.44.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.44.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.44.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.45.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.45.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.45.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.46.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.46.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.46.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.47.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.47.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.47.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.48.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.48.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.48.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.49.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.49.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.49.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.50.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.50.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.50.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.51.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.51.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.51.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.52.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.52.up_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.52.down_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.53.gate_proj.weight": "model-00155-of-000163.safetensors", + "model.layers.59.mlp.experts.53.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.53.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.54.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.54.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.54.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.55.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.55.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.55.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.56.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.56.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.56.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.57.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.57.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.57.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.58.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.58.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.58.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.59.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.59.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.59.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.60.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.60.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.60.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.61.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.61.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.61.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.62.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.62.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.62.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.63.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.63.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.63.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.64.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.64.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.64.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.65.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.65.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.65.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.66.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.66.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.66.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.67.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.67.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.67.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.68.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.68.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.68.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.69.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.69.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.69.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.70.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.70.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.70.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.71.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.71.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.71.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.72.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.72.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.72.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.73.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.73.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.73.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.74.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.74.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.74.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.75.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.75.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.75.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.76.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.76.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.76.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.77.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.77.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.77.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.78.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.78.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.78.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.79.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.79.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.79.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.80.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.80.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.80.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.81.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.81.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.81.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.82.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.82.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.82.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.83.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.83.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.83.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.84.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.84.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.84.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.85.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.85.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.85.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.86.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.86.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.86.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.87.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.87.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.87.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.88.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.88.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.88.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.89.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.89.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.89.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.90.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.90.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.90.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.91.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.91.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.91.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.92.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.92.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.92.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.93.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.93.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.93.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.94.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.94.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.94.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.95.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.95.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.95.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.96.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.96.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.96.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.97.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.97.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.97.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.98.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.98.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.98.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.99.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.99.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.99.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.100.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.100.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.100.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.101.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.101.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.101.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.102.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.102.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.102.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.103.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.103.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.103.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.104.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.104.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.104.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.105.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.105.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.105.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.106.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.106.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.106.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.107.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.107.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.107.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.108.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.108.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.108.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.109.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.109.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.109.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.110.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.110.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.110.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.111.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.111.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.111.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.112.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.112.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.112.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.113.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.113.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.113.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.114.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.114.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.114.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.115.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.115.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.115.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.116.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.116.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.116.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.117.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.117.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.117.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.118.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.118.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.118.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.119.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.119.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.119.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.120.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.120.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.120.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.121.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.121.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.121.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.122.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.122.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.122.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.123.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.123.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.123.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.124.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.124.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.124.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.125.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.125.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.125.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.126.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.126.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.126.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.127.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.127.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.127.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.128.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.128.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.128.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.129.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.129.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.129.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.130.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.130.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.130.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.131.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.131.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.131.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.132.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.132.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.132.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.133.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.133.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.133.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.134.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.134.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.134.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.135.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.135.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.135.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.136.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.136.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.136.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.137.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.137.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.137.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.138.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.138.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.138.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.139.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.139.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.139.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.140.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.140.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.140.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.141.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.141.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.141.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.142.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.142.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.142.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.143.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.143.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.143.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.144.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.144.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.144.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.145.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.145.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.145.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.146.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.146.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.146.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.147.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.147.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.147.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.148.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.148.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.148.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.149.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.149.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.149.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.150.gate_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.150.up_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.150.down_proj.weight": "model-00156-of-000163.safetensors", + "model.layers.59.mlp.experts.151.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.151.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.151.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.152.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.152.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.152.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.153.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.153.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.153.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.154.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.154.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.154.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.155.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.155.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.155.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.156.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.156.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.156.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.157.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.157.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.157.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.158.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.158.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.158.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.159.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.159.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.159.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.160.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.160.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.160.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.161.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.161.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.161.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.162.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.162.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.162.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.163.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.163.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.163.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.164.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.164.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.164.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.165.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.165.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.165.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.166.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.166.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.166.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.167.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.167.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.167.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.168.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.168.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.168.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.169.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.169.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.169.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.170.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.170.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.170.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.171.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.171.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.171.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.172.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.172.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.172.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.173.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.173.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.173.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.174.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.174.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.174.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.175.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.175.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.175.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.176.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.176.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.176.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.177.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.177.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.177.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.178.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.178.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.178.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.179.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.179.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.179.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.180.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.180.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.180.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.181.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.181.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.181.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.182.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.182.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.182.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.183.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.183.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.183.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.184.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.184.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.184.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.185.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.185.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.185.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.186.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.186.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.186.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.187.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.187.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.187.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.188.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.188.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.188.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.189.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.189.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.189.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.190.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.190.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.190.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.191.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.191.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.191.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.192.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.192.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.192.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.193.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.193.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.193.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.194.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.194.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.194.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.195.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.195.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.195.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.196.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.196.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.196.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.197.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.197.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.197.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.198.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.198.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.198.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.199.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.199.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.199.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.200.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.200.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.200.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.201.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.201.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.201.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.202.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.202.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.202.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.203.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.203.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.203.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.204.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.204.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.204.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.205.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.205.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.205.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.206.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.206.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.206.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.207.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.207.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.207.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.208.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.208.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.208.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.209.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.209.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.209.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.210.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.210.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.210.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.211.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.211.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.211.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.212.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.212.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.212.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.213.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.213.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.213.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.214.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.214.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.214.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.215.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.215.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.215.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.216.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.216.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.216.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.217.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.217.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.217.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.218.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.218.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.218.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.219.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.219.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.219.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.220.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.220.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.220.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.221.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.221.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.221.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.222.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.222.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.222.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.223.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.223.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.223.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.224.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.224.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.224.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.225.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.225.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.225.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.226.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.226.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.226.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.227.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.227.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.227.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.228.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.228.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.228.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.229.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.229.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.229.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.230.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.230.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.230.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.231.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.231.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.231.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.232.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.232.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.232.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.233.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.233.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.233.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.234.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.234.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.234.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.235.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.235.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.235.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.236.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.236.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.236.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.237.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.237.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.237.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.238.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.238.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.238.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.239.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.239.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.239.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.240.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.240.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.240.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.241.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.241.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.241.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.242.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.242.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.242.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.243.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.243.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.243.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.244.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.244.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.244.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.245.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.245.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.245.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.246.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.246.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.246.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.247.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.247.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.247.down_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.248.gate_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.248.up_proj.weight": "model-00157-of-000163.safetensors", + "model.layers.59.mlp.experts.248.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.249.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.249.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.249.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.250.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.250.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.250.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.251.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.251.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.251.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.252.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.252.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.252.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.253.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.253.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.253.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.254.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.254.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.254.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.255.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.255.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.mlp.experts.255.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.59.input_layernorm.weight": "model-00158-of-000163.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.q_a_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.q_a_layernorm.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.q_b_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.kv_a_proj_with_mqa.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.kv_a_layernorm.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.kv_b_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.indexer.wq_b.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.indexer.wk.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.indexer.k_norm.weight": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.indexer.k_norm.bias": "model-00158-of-000163.safetensors", + "model.layers.60.self_attn.indexer.weights_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.gate.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.gate.e_score_correction_bias": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.shared_experts.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.shared_experts.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.shared_experts.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.0.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.0.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.0.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.1.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.1.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.1.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.2.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.2.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.2.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.3.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.3.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.3.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.4.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.4.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.4.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.5.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.5.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.5.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.6.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.6.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.6.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.7.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.7.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.7.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.8.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.8.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.8.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.9.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.9.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.9.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.10.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.10.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.10.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.11.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.11.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.11.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.12.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.12.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.12.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.13.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.13.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.13.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.14.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.14.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.14.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.15.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.15.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.15.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.16.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.16.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.16.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.17.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.17.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.17.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.18.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.18.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.18.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.19.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.19.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.19.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.20.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.20.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.20.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.21.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.21.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.21.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.22.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.22.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.22.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.23.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.23.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.23.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.24.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.24.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.24.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.25.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.25.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.25.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.26.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.26.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.26.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.27.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.27.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.27.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.28.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.28.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.28.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.29.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.29.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.29.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.30.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.30.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.30.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.31.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.31.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.31.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.32.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.32.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.32.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.33.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.33.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.33.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.34.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.34.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.34.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.35.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.35.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.35.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.36.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.36.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.36.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.37.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.37.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.37.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.38.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.38.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.38.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.39.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.39.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.39.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.40.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.40.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.40.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.41.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.41.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.41.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.42.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.42.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.42.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.43.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.43.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.43.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.44.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.44.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.44.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.45.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.45.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.45.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.46.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.46.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.46.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.47.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.47.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.47.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.48.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.48.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.48.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.49.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.49.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.49.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.50.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.50.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.50.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.51.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.51.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.51.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.52.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.52.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.52.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.53.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.53.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.53.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.54.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.54.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.54.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.55.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.55.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.55.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.56.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.56.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.56.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.57.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.57.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.57.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.58.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.58.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.58.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.59.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.59.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.59.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.60.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.60.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.60.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.61.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.61.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.61.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.62.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.62.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.62.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.63.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.63.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.63.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.64.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.64.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.64.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.65.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.65.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.65.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.66.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.66.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.66.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.67.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.67.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.67.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.68.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.68.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.68.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.69.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.69.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.69.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.70.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.70.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.70.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.71.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.71.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.71.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.72.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.72.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.72.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.73.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.73.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.73.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.74.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.74.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.74.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.75.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.75.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.75.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.76.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.76.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.76.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.77.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.77.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.77.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.78.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.78.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.78.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.79.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.79.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.79.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.80.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.80.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.80.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.81.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.81.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.81.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.82.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.82.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.82.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.83.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.83.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.83.down_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.84.gate_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.84.up_proj.weight": "model-00158-of-000163.safetensors", + "model.layers.60.mlp.experts.84.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.85.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.85.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.85.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.86.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.86.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.86.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.87.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.87.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.87.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.88.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.88.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.88.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.89.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.89.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.89.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.90.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.90.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.90.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.91.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.91.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.91.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.92.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.92.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.92.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.93.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.93.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.93.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.94.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.94.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.94.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.95.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.95.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.95.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.96.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.96.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.96.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.97.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.97.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.97.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.98.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.98.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.98.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.99.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.99.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.99.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.100.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.100.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.100.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.101.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.101.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.101.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.102.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.102.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.102.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.103.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.103.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.103.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.104.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.104.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.104.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.105.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.105.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.105.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.106.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.106.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.106.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.107.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.107.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.107.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.108.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.108.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.108.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.109.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.109.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.109.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.110.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.110.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.110.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.111.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.111.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.111.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.112.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.112.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.112.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.113.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.113.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.113.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.114.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.114.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.114.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.115.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.115.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.115.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.116.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.116.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.116.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.117.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.117.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.117.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.118.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.118.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.118.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.119.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.119.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.119.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.120.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.120.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.120.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.121.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.121.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.121.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.122.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.122.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.122.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.123.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.123.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.123.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.124.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.124.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.124.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.125.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.125.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.125.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.126.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.126.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.126.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.127.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.127.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.127.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.128.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.128.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.128.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.129.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.129.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.129.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.130.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.130.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.130.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.131.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.131.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.131.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.132.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.132.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.132.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.133.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.133.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.133.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.134.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.134.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.134.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.135.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.135.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.135.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.136.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.136.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.136.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.137.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.137.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.137.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.138.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.138.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.138.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.139.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.139.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.139.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.140.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.140.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.140.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.141.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.141.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.141.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.142.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.142.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.142.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.143.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.143.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.143.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.144.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.144.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.144.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.145.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.145.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.145.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.146.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.146.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.146.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.147.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.147.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.147.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.148.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.148.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.148.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.149.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.149.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.149.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.150.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.150.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.150.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.151.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.151.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.151.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.152.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.152.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.152.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.153.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.153.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.153.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.154.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.154.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.154.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.155.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.155.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.155.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.156.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.156.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.156.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.157.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.157.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.157.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.158.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.158.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.158.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.159.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.159.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.159.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.160.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.160.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.160.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.161.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.161.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.161.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.162.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.162.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.162.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.163.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.163.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.163.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.164.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.164.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.164.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.165.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.165.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.165.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.166.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.166.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.166.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.167.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.167.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.167.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.168.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.168.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.168.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.169.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.169.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.169.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.170.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.170.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.170.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.171.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.171.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.171.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.172.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.172.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.172.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.173.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.173.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.173.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.174.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.174.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.174.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.175.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.175.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.175.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.176.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.176.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.176.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.177.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.177.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.177.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.178.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.178.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.178.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.179.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.179.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.179.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.180.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.180.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.180.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.181.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.181.up_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.181.down_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.182.gate_proj.weight": "model-00159-of-000163.safetensors", + "model.layers.60.mlp.experts.182.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.182.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.183.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.183.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.183.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.184.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.184.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.184.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.185.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.185.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.185.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.186.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.186.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.186.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.187.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.187.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.187.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.188.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.188.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.188.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.189.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.189.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.189.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.190.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.190.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.190.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.191.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.191.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.191.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.192.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.192.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.192.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.193.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.193.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.193.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.194.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.194.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.194.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.195.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.195.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.195.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.196.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.196.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.196.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.197.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.197.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.197.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.198.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.198.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.198.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.199.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.199.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.199.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.200.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.200.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.200.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.201.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.201.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.201.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.202.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.202.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.202.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.203.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.203.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.203.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.204.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.204.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.204.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.205.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.205.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.205.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.206.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.206.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.206.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.207.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.207.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.207.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.208.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.208.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.208.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.209.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.209.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.209.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.210.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.210.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.210.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.211.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.211.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.211.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.212.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.212.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.212.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.213.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.213.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.213.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.214.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.214.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.214.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.215.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.215.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.215.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.216.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.216.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.216.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.217.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.217.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.217.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.218.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.218.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.218.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.219.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.219.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.219.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.220.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.220.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.220.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.221.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.221.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.221.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.222.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.222.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.222.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.223.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.223.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.223.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.224.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.224.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.224.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.225.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.225.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.225.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.226.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.226.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.226.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.227.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.227.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.227.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.228.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.228.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.228.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.229.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.229.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.229.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.230.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.230.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.230.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.231.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.231.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.231.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.232.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.232.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.232.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.233.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.233.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.233.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.234.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.234.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.234.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.235.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.235.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.235.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.236.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.236.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.236.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.237.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.237.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.237.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.238.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.238.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.238.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.239.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.239.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.239.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.240.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.240.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.240.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.241.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.241.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.241.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.242.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.242.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.242.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.243.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.243.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.243.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.244.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.244.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.244.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.245.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.245.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.245.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.246.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.246.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.246.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.247.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.247.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.247.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.248.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.248.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.248.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.249.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.249.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.249.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.250.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.250.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.250.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.251.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.251.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.251.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.252.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.252.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.252.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.253.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.253.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.253.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.254.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.254.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.254.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.255.gate_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.255.up_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.mlp.experts.255.down_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.60.input_layernorm.weight": "model-00160-of-000163.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00160-of-000163.safetensors", + "model.norm.weight": "model-00160-of-000163.safetensors", + "lm_head.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.q_a_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.q_a_layernorm.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.q_b_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.kv_a_proj_with_mqa.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.kv_a_layernorm.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.kv_b_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00160-of-000163.safetensors", + "model.layers.61.self_attn.indexer.wq_b.weight": "model-00161-of-000163.safetensors", + "model.layers.61.self_attn.indexer.wk.weight": "model-00161-of-000163.safetensors", + "model.layers.61.self_attn.indexer.k_norm.weight": "model-00161-of-000163.safetensors", + "model.layers.61.self_attn.indexer.k_norm.bias": "model-00161-of-000163.safetensors", + "model.layers.61.self_attn.indexer.weights_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.gate.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.gate.e_score_correction_bias": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.shared_experts.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.shared_experts.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.shared_experts.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.0.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.0.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.0.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.1.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.1.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.1.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.2.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.2.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.2.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.3.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.3.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.3.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.4.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.4.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.4.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.5.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.5.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.5.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.6.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.6.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.6.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.7.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.7.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.7.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.8.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.8.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.8.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.9.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.9.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.9.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.10.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.10.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.10.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.11.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.11.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.11.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.12.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.12.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.12.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.13.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.13.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.13.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.14.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.14.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.14.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.15.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.15.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.15.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.16.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.16.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.16.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.17.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.17.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.17.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.18.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.18.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.18.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.19.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.19.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.19.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.20.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.20.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.20.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.21.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.21.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.21.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.22.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.22.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.22.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.23.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.23.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.23.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.24.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.24.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.24.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.25.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.25.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.25.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.26.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.26.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.26.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.27.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.27.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.27.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.28.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.28.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.28.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.29.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.29.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.29.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.30.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.30.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.30.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.31.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.31.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.31.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.32.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.32.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.32.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.33.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.33.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.33.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.34.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.34.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.34.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.35.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.35.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.35.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.36.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.36.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.36.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.37.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.37.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.37.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.38.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.38.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.38.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.39.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.39.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.39.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.40.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.40.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.40.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.41.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.41.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.41.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.42.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.42.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.42.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.43.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.43.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.43.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.44.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.44.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.44.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.45.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.45.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.45.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.46.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.46.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.46.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.47.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.47.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.47.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.48.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.48.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.48.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.49.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.49.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.49.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.50.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.50.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.50.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.51.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.51.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.51.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.52.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.52.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.52.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.53.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.53.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.53.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.54.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.54.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.54.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.55.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.55.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.55.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.56.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.56.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.56.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.57.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.57.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.57.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.58.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.58.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.58.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.59.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.59.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.59.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.60.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.60.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.60.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.61.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.61.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.61.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.62.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.62.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.62.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.63.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.63.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.63.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.64.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.64.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.64.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.65.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.65.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.65.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.66.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.66.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.66.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.67.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.67.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.67.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.68.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.68.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.68.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.69.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.69.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.69.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.70.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.70.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.70.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.71.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.71.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.71.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.72.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.72.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.72.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.73.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.73.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.73.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.74.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.74.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.74.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.75.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.75.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.75.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.76.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.76.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.76.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.77.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.77.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.77.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.78.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.78.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.78.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.79.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.79.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.79.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.80.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.80.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.80.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.81.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.81.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.81.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.82.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.82.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.82.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.83.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.83.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.83.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.84.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.84.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.84.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.85.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.85.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.85.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.86.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.86.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.86.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.87.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.87.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.87.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.88.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.88.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.88.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.89.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.89.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.89.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.90.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.90.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.90.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.91.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.91.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.91.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.92.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.92.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.92.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.93.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.93.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.93.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.94.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.94.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.94.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.95.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.95.up_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.95.down_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.96.gate_proj.weight": "model-00161-of-000163.safetensors", + "model.layers.61.mlp.experts.96.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.96.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.97.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.97.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.97.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.98.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.98.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.98.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.99.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.99.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.99.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.100.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.100.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.100.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.101.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.101.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.101.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.102.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.102.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.102.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.103.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.103.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.103.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.104.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.104.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.104.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.105.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.105.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.105.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.106.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.106.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.106.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.107.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.107.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.107.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.108.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.108.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.108.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.109.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.109.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.109.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.110.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.110.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.110.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.111.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.111.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.111.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.112.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.112.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.112.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.113.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.113.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.113.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.114.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.114.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.114.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.115.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.115.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.115.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.116.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.116.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.116.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.117.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.117.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.117.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.118.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.118.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.118.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.119.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.119.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.119.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.120.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.120.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.120.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.121.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.121.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.121.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.122.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.122.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.122.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.123.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.123.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.123.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.124.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.124.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.124.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.125.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.125.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.125.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.126.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.126.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.126.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.127.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.127.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.127.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.128.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.128.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.128.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.129.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.129.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.129.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.130.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.130.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.130.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.131.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.131.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.131.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.132.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.132.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.132.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.133.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.133.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.133.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.134.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.134.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.134.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.135.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.135.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.135.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.136.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.136.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.136.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.137.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.137.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.137.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.138.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.138.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.138.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.139.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.139.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.139.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.140.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.140.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.140.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.141.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.141.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.141.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.142.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.142.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.142.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.143.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.143.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.143.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.144.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.144.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.144.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.145.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.145.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.145.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.146.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.146.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.146.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.147.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.147.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.147.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.148.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.148.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.148.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.149.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.149.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.149.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.150.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.150.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.150.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.151.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.151.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.151.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.152.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.152.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.152.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.153.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.153.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.153.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.154.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.154.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.154.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.155.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.155.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.155.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.156.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.156.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.156.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.157.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.157.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.157.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.158.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.158.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.158.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.159.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.159.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.159.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.160.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.160.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.160.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.161.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.161.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.161.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.162.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.162.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.162.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.163.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.163.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.163.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.164.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.164.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.164.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.165.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.165.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.165.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.166.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.166.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.166.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.167.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.167.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.167.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.168.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.168.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.168.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.169.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.169.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.169.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.170.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.170.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.170.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.171.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.171.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.171.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.172.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.172.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.172.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.173.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.173.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.173.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.174.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.174.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.174.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.175.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.175.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.175.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.176.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.176.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.176.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.177.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.177.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.177.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.178.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.178.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.178.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.179.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.179.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.179.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.180.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.180.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.180.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.181.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.181.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.181.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.182.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.182.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.182.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.183.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.183.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.183.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.184.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.184.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.184.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.185.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.185.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.185.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.186.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.186.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.186.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.187.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.187.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.187.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.188.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.188.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.188.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.189.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.189.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.189.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.190.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.190.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.190.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.191.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.191.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.191.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.192.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.192.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.192.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.193.gate_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.193.up_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.193.down_proj.weight": "model-00162-of-000163.safetensors", + "model.layers.61.mlp.experts.194.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.194.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.194.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.195.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.195.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.195.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.196.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.196.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.196.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.197.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.197.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.197.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.198.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.198.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.198.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.199.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.199.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.199.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.200.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.200.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.200.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.201.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.201.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.201.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.202.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.202.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.202.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.203.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.203.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.203.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.204.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.204.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.204.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.205.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.205.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.205.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.206.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.206.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.206.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.207.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.207.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.207.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.208.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.208.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.208.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.209.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.209.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.209.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.210.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.210.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.210.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.211.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.211.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.211.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.212.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.212.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.212.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.213.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.213.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.213.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.214.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.214.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.214.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.215.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.215.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.215.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.216.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.216.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.216.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.217.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.217.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.217.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.218.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.218.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.218.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.219.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.219.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.219.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.220.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.220.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.220.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.221.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.221.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.221.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.222.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.222.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.222.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.223.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.223.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.223.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.224.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.224.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.224.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.225.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.225.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.225.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.226.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.226.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.226.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.227.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.227.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.227.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.228.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.228.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.228.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.229.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.229.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.229.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.230.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.230.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.230.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.231.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.231.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.231.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.232.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.232.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.232.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.233.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.233.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.233.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.234.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.234.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.234.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.235.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.235.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.235.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.236.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.236.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.236.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.237.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.237.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.237.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.238.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.238.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.238.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.239.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.239.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.239.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.240.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.240.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.240.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.241.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.241.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.241.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.242.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.242.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.242.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.243.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.243.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.243.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.244.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.244.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.244.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.245.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.245.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.245.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.246.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.246.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.246.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.247.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.247.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.247.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.248.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.248.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.248.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.249.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.249.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.249.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.250.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.250.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.250.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.251.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.251.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.251.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.252.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.252.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.252.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.253.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.253.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.253.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.254.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.254.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.254.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.255.gate_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.255.up_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.mlp.experts.255.down_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.input_layernorm.weight": "model-00163-of-000163.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00163-of-000163.safetensors", + "model.layers.61.embed_tokens.weight": "model-00163-of-000163.safetensors", + "model.layers.61.enorm.weight": "model-00163-of-000163.safetensors", + "model.layers.61.hnorm.weight": "model-00163-of-000163.safetensors", + "model.layers.61.eh_proj.weight": "model-00163-of-000163.safetensors", + "model.layers.61.shared_head.norm.weight": "model-00163-of-000163.safetensors", + "model.layers.61.shared_head.head.weight": "model-00163-of-000163.safetensors" + } +} \ No newline at end of file diff --git a/bf16/upload_bf16.py b/bf16/upload_bf16.py new file mode 100644 index 0000000000000000000000000000000000000000..a31df63c5924ce72b6171eb7f3e20d6593737069 --- /dev/null +++ b/bf16/upload_bf16.py @@ -0,0 +1,10 @@ +from huggingface_hub import HfApi +import os + +api = HfApi(token=os.getenv("HF_TOKEN")) +api.upload_folder( + folder_path="/data2/DeepSeek-V3.2-bf16", + repo_id="createthis/DeepSeek-V3.2-bf16", + repo_type="model", + path_in_repo="bf16" +)