diff --git a/checkpoints/Qwen3-8B-Base/0.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/0.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..802790fe6c7b9618a746a437199ebbf48422c700 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2301f4ac671e2765a1bd0848354169a2f86cda4cad27dce83dbfc2b7f8c9d6 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/0.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/0.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..016f0d45b24bdf97acd8a20ea8633ee54d509715 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31a4fe8ebcf3fdeda6bc95f32596fd2dc01ee8e8a1f58e71bc4d6341287f0e8b +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/0.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/0.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3b6b83da8b020f42292898abb5ae30d07ce805ca --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d0d2a78cafc7ad7e4b494fe6f8ae157b22e792fdc8ff060f5185b4c7a55c07 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/0.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/0.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2b0a2fa385b5fb6989158df34e563ffab3a13ff6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33445ee4c2babaddb4c59ab49bab3307158f68f6672faa43d3e90430500c11f +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/0.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/0.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8fce11a45492cd5ced8a3dfd95b52e665f5a2b12 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8179164bb304959af0cebdc58c4cb93fa2c24cc32a248804308518ebe181a6f0 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/0.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/0.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..287b406a9258e3589f05f0b68e0ce31b78bbcf5b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ddf2ac8479e5059702d41d415be7c7887186fa4fcc1b6c40f776d0c34667f30 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/0.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/0.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..adc2a4e93e55cf0e4883ccf83c4fc54eb880a8ca --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/0.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6fbbf4f2398a69b709d82000def3e73dd8add95b7d99b651d062c81c3399523 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/1.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/1.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f7263c52446fa9fb6885bea1e587b5231c46f0a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5217d42657184b110f21518c5c5b1da915ecaea7f6cd9b9c0ef49ae541c06945 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/1.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/1.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a98942e9affbd97dbe9d9db0eb97b75b8cd15cf --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed598f2c0bf2f094b454566d7b56fcf3a69176945b10ce85bfe3211f546b1c48 +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/1.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/1.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..79e56be97259c9a761fd4119a8b50ce408d1860c --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf26f21116706df2de8e9f1e5c96ae652ebcf44a53e56d87dd1bc5a63b7dbaca +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/1.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/1.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c87427767b457d9a10973857be17481ce822baa --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4f683622cbdfd61c3e5725be1e56a1d59e2a00c170e1454a8baad2fabf6f97 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/1.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/1.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..eeb062857ffe8c968b3a234a580c6115c0b73e52 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f36625a5b16c6b115f64cacac8e82481f452301af9683a38ea32ec4ccd487a3 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/1.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/1.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcba137892114b11b949f7da515f578870f1a41a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02ecdac6c5cff9be89540797c2177c1a868134867fdf1648736501b04cb9110 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/1.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/1.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4f0993fcf00efdc9d70169509b2759a17d4f567 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/1.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624b6fe1d9996d2d5f6924885e76a595a69a616a281d1272d899448998d10ca7 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/10.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/10.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..89f7864b5bc4e35cb7b82191ccebe37d40eea3af --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6068a936f960d7f7f405a497b6173ad2be1beb6fbb6da5ff8907b30ac0571895 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/10.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/10.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a82d3a83be63c697a7a67098cfdbb0429ed67ec9 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4d4dc190a32c362157ce2fcffb3f3ed380d80b769413b602a4448f2885d796 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/10.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/10.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8159fec44481e62b6560845ecf62e28155752d4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5b5cf778aed07fad01423b348f0f191a18a4b1930cbe9e797b9c0cdf7736d7 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/10.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/10.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..47b421c8473dd3856291dde8aa7fde45d9122aeb --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a770b65403d3f1a3ed31d88945e73bbcf076f3a6c11d59c883cb01e2124c9b7 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/10.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/10.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..515f1a94de9dffb3ca2f3be7b1d24f6849749ce1 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e73021b789d8f2ff7e31b624e4acee772a7a0ba400af4dd8b1f9fb85356a2d +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/10.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/10.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a251fe7aeae3eb99535b66b306eb9c0089d8419 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2f24106c651adb598ce984f7d18d2a5de1a9518cfa5a37909e8e583a71f9bed +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/10.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/10.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c21efbc90c579e289c5f7b3964f30540b5c5cacb --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/10.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb1add70aaa66cb601ef22370e03a41cb66d733cfac0b55476cf099d6ad3673a +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/11.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/11.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8eae673ebded2f599e9d908997f0f0bbdc9133b8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7513e986ce2f27849a396cbc0d1e1251efeca3800d62cb4770e267b0ee518887 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/11.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/11.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..643b92cc01f421e72fce5e68709bbe29e6241d89 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adccf5dadba3fc776ee2ca11a7181840a702d30c62c6656d8508b9ab5c3252c2 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/11.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/11.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a44659e6fe2d859be9106e5ff835f020946b4be6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8475e589537fc29003ed05bae98c953a1c2f62e86156c119e16f0e1027361c +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/11.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/11.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e590c144f0e7001e5d87ef50d3860d624c23a4d0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5845eb1d0a941abda37fb79f93cf938e4ebfab441a822293309373f96e32fb0d +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/11.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/11.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a9e735a5405f05f7a49be538d0a8ddfadd25fea --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2bcca6e7082d806c22a0d268596c06b63eb941a6078a700d39554d0d1721d9f +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/11.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/11.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..922a372ea8faf7c5eb04743de3f14f5436c6f89a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228c7cc65b257831a4568836fed6a820fdfe60ae15a46a7282345cf18b1c5750 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/11.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/11.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb739e7c462bd5bad04b4f44395eaffa4b79a35b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/11.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20498fa6ed9fa4672425385741db1f39158eba538503e61a2461a3f31628429c +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/12.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/12.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b65ed42f8dfd7d1025644d66d45b8ece302d7c3 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82f0f5062c438392c0ce9ba39af6a8c3788ae0e51a4a2ad6ca458b49cb0f152 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/12.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/12.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0ef43f183f7350d10264ac84c3c315050753cc1e --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:805111de8675dff88432c6f0abc7d48a01fb04e5bca31dc471e50fea966d1329 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/12.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/12.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..af0597674fa25bb61a210f17bb06caf790618ce7 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9338f1aa12427e7673d9d5cb8f17e8e6c4a47acac3c2a19adaadb221ba93d653 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/12.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/12.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..90a481cf0e13e42b54e5a724de97d7d817230db8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c46de96903547797dc3438fcb8fc6bd39dfe700622f859a3b745de40f996aa8 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/12.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/12.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3f0fbf1ea21fc6fa368ebb51d837b148444a8563 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610030c770131eb1e0561fd6f1c6e4669c4007697a3cf0a220cca3bbfbb19112 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/12.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/12.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..63ff91a263fce3c8b0f428b19f7999754933b774 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f2a62e4e16512d55bd3c3010204f7881b6748127bd4e0f113c04640682d270 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/12.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/12.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d1f48aef938c41590664f771f311e759e208900 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/12.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf76e7e3ce5c37ff9ed7d5fc20bff5f2d9a2263794e7ef49c2604ceae7477d8 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/13.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/13.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d4d458a56c1281e81bde6899aa54379ac53845be --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454c6eb8d958f09204d71d13230b5e60588bf962ad43ec599157a6d5785cdefe +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/13.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/13.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a3bbc9ca169f58b82c920e064d3acb05e03419b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a3cdc0b657452733c5e2d2dadc18b4364f3406450ab4fd954d0131ba30dc65 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/13.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/13.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4bcadd62b49e5804b74f6998faecfd8086bb5bc6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bacfa0872606b2ca67bfba672cfbb6ef62811726d080af1a5f2a1fe2c9e5685f +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/13.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/13.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bef03256479576fb1a4df25f31a750b4c6e34c2 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd45699efc442a4d046803ac4708f949065152f2e68f24a66eef3166ac8915f4 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/13.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/13.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2810bdfb3b4da1450c4a41106c01abf074805400 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:909431b29bf607a78a4ee4935d82e0abc25997667300ce52d13a689ddd414ce0 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/13.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/13.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..876e0402e0218d9ab4c39cd05f5595dfe1058670 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ec1c86a93035e4a89e420426047dae2e687a028ab7730cdde3e76b16516d517 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/13.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/13.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..8621243e86001604530ed2471cdc2c1280682152 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/13.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c2da8c86f917641935184c3e269ed5427931dd7eeb40e025168efcb8aae97e +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/14.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/14.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..13639be199a4fa34105a701c359c6a4e53192133 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8104528548ef850e038bf05204df4272c60266facba96561d988395d66b306a +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/14.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/14.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1f39603cd9f8c2742f738916401f9470379afe96 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb1a35ec4be9787b7f9669d55b748e22cd6336dc51ce3f00dc72a14a2311e04 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/14.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/14.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7cc68dd6b6cd02b810b36a40b4bfa148184841f5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf667dcc3355c1bcff474f68db67165c3ecff2d68d401650efdd75c892ca624 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/14.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/14.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0d3b33f1971e0fcc836bb1ffdce740218fe7baa --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1029edec1e8f6d951e799c7ecf279f0bdfedd0b2d55dfafe58c69c7fb8be92 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/14.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/14.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2cccfef4ae5ec562e6da35cdca0f63592e7595d8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f00a58ad178201627c37d2cef220fe5d943c7b9e6b99d375a727d4d6e4367bb7 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/14.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/14.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7879704d64e6762ae03447cd0b3981134469f7a4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cc37ec797af1ad1c20e85e442d0b1f7fb657127d64388f338209fff2c06fd84 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/14.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/14.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0473968609dfdb6b465e5fc5966863aeaf4ec696 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/14.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de3b02e020f278c5036cb4a0aefc1c0978cb1b9bbcafc13fea3a3ad1fde8e6c6 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/15.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/15.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5ab1b046d06c73e1e13045b392057146996c43a0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f46a3cd08d27fefaab0b1f49d555001f14a3a354ea493c38b02078f09dc26b0 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/15.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/15.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b072726dea302b56679c901014b85f6e69592c89 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:650be99eaccd751f070b076ccdfd8cb96525c3d84b77613c9e42a620525619b6 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/15.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/15.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e75dcfdc967ea671393723a65eaf0ff89b0f978 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f641d08627ed3fb5966550a7b882d6d0c4a40e4a5c9978c6d66b57d03f4d441 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/15.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/15.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..655ecb8099bcb0b11aab0d0af1acb83c322a7bde --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ecc32a51f13ea1442a593986edb394eeb9cc45e3ec139929a73006a33bff34 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/15.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/15.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b5cb800679152c34e79241e5f91d7a843d8f0983 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91817c5ef43e3ccff658af410175e3444c4e133a1ab1976046580133de66f644 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/15.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/15.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d07daced6630eff0be619c4bd33bb3c55b0631d4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006a34d380ae5f05cf88cc55765026a739d2967411a9ccd9b62fa00d0bd9b3f3 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/15.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/15.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e354c957b407a2a60eadc3c9827fd29b5126323 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/15.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a22f9da31074c5940c4b959a141a362a5375250d930eb2c68571898fb8019ed +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/16.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/16.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7272f12b82d4d8bddb816594c0e17c3b66c478dd --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e6d5b0d446805c5f69958a213bee25643cdd995f96623088567507937b66ca +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/16.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/16.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0d37511b4d585561b1f00267063d343447f39b4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3515b4eeb1a99ee78ee9364b31df0a0a118869c63624e9bc9b6174e440db6c24 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/16.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/16.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d84bf5d6627c7bb06fb295375a3e17a057e65a62 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf28113da5473b4056ebaa776ea0ab511963a5ae6edb6a4ef4dc720d1b6a5248 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/16.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/16.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dcc6c04026ca664144a603af5e217245ac4ede1f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e8dbd3d0bf9ab88ea760671b30937a4a80d0fa867494111db3af8eccd1f465 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/16.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/16.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9f52abf58f0292163cc9c1de1aeddd27fc940963 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cfb8710c208da8b26378da238351af77b2ca2390c9cfa9f8d6b1bf124ff2498 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/16.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/16.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fb9e4f744c8ee537f122c970f3e9fdf9efa01de5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1770de67075f2868bea84f755d042e9689f273d03af8e937557bcd828b0109c7 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/16.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/16.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9417e2e66ab542a8333334669e8af75d3b4b793f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/16.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35da7ae34fc66fb8852150416cb1ce39d3f2fb4eb527085e568fa917e86a209 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/17.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/17.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f3439492dc340d133d5f51fd798f26abac47a3c --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9f6227f7b274a96b05d94552f234dcb4883ed4203130922477303bdc4bbd8f +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/17.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/17.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d62e9fd7b5b52a00a8b14f7c040a5c52e9f6441 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a388b16884535c7795533d9fd51ed9e3fb84081d2b9bd516c3bc5a6cc2cca526 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/17.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/17.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f4eab1a4ce20f0853b5e4bff9a2248454fccca8a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2804eb7557b841ce23e73bd63172fe0bcaa863377265d97ee14480f8c52426c6 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/17.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/17.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..06a911c227c7c4761414f08c8b2b9ac44b90a51a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9b755dc747d5ae7dec00f01cafb1a41c1930f1661c43bbb863de7cc1388823b +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/17.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/17.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ac8d5197793372d3d7dff21950f7d1c588e5f250 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46182a74e769ca81cb0049c867aa1fd98b357b394138cb41f429b25145c60d83 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/17.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/17.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9da691158d8aa7c22beacee3e4c627ca81efaf00 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8550c6888e856dbe9453e3f09c69cb04d22c99ecef2f6447edf134b01253bf8b +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/17.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/17.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab3cd32a40115838567663258a12642e3b1e6006 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/17.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dab0fca3acc2f458ac2a8c2730e32861990d9c732645541ce8b5e8d0de6ee62a +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/18.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/18.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e2c986cb25bb3e857f61b4d539cd66a8c9d9549 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa805995b06f612511889c0b5050a7577bdb9bd52d7ea00d5366ea62f2bed7fa +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/18.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/18.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2d5eb2d551929d487f5c90b822bffb1203849a6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f613393ede26812ae7810db2d40f123cffa94cb8a5bf3c9bcc04dcfdc2d84d0f +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/18.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/18.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5425050d43a207347494d2787a3fbd77e31a7d16 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f4ab936e73af1422ed9c56f8cce04776573bbaae07f457c4cad39b3362e722 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/18.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/18.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..78e6873a5fc8561a6292d629656283c42e92b8a0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786d5ddc64ea11ac636f2d3f67a357d9761cd4a7f9a1da71b272df329e34ec84 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/18.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/18.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..30fe109048d04db65a919d84f506e19ca64dee10 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d6752551df8c7735f09cc423b257c3a0ce79854321f11f502d92afaf780539 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/18.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/18.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7a1e867cfc6a309fd0654e6fa7fe91a59bfc2c34 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27bbada44ce3941477942af87d0499d371161204fccb4b835b721444c4a35bb5 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/18.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/18.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d8359d847a3c67a8fcb773f43245b7d162769a64 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/18.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:779e121a3df0faa4c21f518fd0dbf3e9baf246e56401a8ee8b8591b3d940cc24 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/19.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/19.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..143abe7a1464b4ce296e89b58c523837aeca6f28 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1940e4a4b4d2d25b07e27172a5a2e1e27f9e9d4b290998f75166fc354d7f98 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/19.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/19.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1af80191984072432b9afad44f4c5dc59d53f11f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d65fc7877a072024b6515e4373e7564b443aaf2d00f23141dd8c6d479d365ea +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/19.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/19.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e0ec81af3311f4c3db8c85cbf19c69dcd62b5a5b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4763eb7dcaf449c2ad1dc103363db997aa63c29ff21e83468bc07ca45618fb57 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/19.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/19.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2579b479d8d2b0734d6d9fd11c23b31951afbedd --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:721691e784b79dd825db5398a431f88cb38191151668025d440cf9cd18963e35 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/19.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/19.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e48b7a425c1571147750be2093d764dba20d4572 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b654a0b510f7a26ffab644f61a8fa4f3487972079d712db33f3cdf6d8dba61a2 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/19.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/19.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba1f032aa7f0eb8218412393841d40c6b5ea43f6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6dbf3f786debfdac223922643827497074025a939edebb4d46bb0a8ddc6dc4 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/19.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/19.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..27e1debf04de01ac2674cd62c84f54d824f39b8f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/19.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4be128b2d942e364b9d68c2a537bba293e83080cddd75f164a4afdc742ed381 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/2.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/2.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..488feef5f78b85107fd954f1f8a9c178d54b8025 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9bdd96d5f507dfdddd55d3fa34cb00188a07166134f19b21e111526ff97c408 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/2.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/2.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cee46d28d8f285b13b1decbbfeb7c94d516705b2 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a2dbf7d1ba4008c1a874216571346a83767b76fb07289f6fe22019f2cff52c9 +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/2.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/2.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8309e7f688242a50d019789d4798a967708d029 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14eae81baa107679a27bfb65311c6ed1ddd546a37f9a6c41c50ee8e5bf024e1 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/2.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/2.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2f3639b4e85458a1f72d3070196e92a54c3a271a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5fc1ae9518896db1697884b2198e0c54104be158754c693106fd6a214365f8a +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/2.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/2.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cb3e48d4a91102919ae0b7fece17ae053f3d879d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897470274f8a6cbb5ce8665ea049e89d219ea6378f7ba405c4300cdbcb22f284 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/2.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/2.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4f582145ac99ec38a16ab9934f8544998f39a3a8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be86fd1465e4d43de6b129c4ee115a12f9fbbec1fa0479bc28d07db9f3eb1087 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/2.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/2.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6087a13b24f78d3b9e2841df6507bbed3665c4b8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/2.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1798377652ee08c118719f5548f4f0e90fbfda75269a8b1ee12748b1fd54eea4 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/20.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/20.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cbc66f02a7cc1af2a941690f93d5d37b973ad89d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f54b396938f11edc509f9be78d90cf41d39cf66d2e0242926a49c2d731e23c5 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/20.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/20.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..88154aa898f27e694f09604d360392cf05b8f15d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:829c118537192822246b41a7435dbc14fb889fded439ffbb1c531b5191040813 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/20.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/20.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..22bb3ffdef092484ace6edf134817cfc1b21bb08 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5f7c4bb126006c85e2a032c133bfd3df53bdb44fa7860a334898257454c97c +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/20.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/20.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..68b3d373fe4addf4de2f39b4c18b375a169685f4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec73e37a20a83524975b4d75bef959cbf1b99d3be7c711d3e52b2d1d2a6a8bc5 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/20.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/20.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..346f461d478f29ad41cc848cfa3c87897aa32dde --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bbff3ac298b33e3324b9a04ba4a068f6cb3a429d84b7468fb21ab87b41d3bf1 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/20.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/20.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6bcf757d50c7420c0cb7ac704048a1683eff935f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2346f90c8a4be70be5e9baf07dfff5d4dcd7e82b395c29e6cfb5a0177b79416b +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/20.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/20.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..967ce4d31a341adfe22f3f025c7d152219b4a639 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/20.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4527ba830ea0b6821a30c7133f75b8b5562d5b975fb68c9d9bacaa9603e4323 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/21.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/21.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..60accaa4404db45c9c6e9777c1dfec7b7cac2800 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b88f27c540fa685006327a7d6784433570a6767a1056a58427db5af62b8acc +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/21.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/21.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1459f5c78c66d8fe7dcf890a9ec8154786b28d78 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec0a87f1f95c9c7268fe2e548ef430871f446454b34c0da10e8fc92d6054f2b1 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/21.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/21.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b98fe6eed33269d9b5908d4d2c1202d5b87a2b5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558d80d3018bc03a9cf7e7ce0e545d5e27505c0ccdbfe7bac4120a1d1310e150 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/21.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/21.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1439976903d51989371947f1db8c277186288994 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2192c1d7379d7d84fe1485023d689dceba7d92fb0fbaa719228334a538dca69a +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/21.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/21.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cdbc9555498dd78a0f6e8f111f49ac00590bcc98 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0d6803157d4b16ad98771e67a6bd8da82f0bae92540f5395e5366d2aa60e58 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/21.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/21.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a6383a381e001026d19f0c21e0c40993bb1d1a0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5df4488c9470f6c5611257a58472d22fe3e670069fb44a9b78aa2414c000492c +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/21.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/21.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ada2a2167a7a1488d5df665fd9182127928533df --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/21.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3da0cba078681e0979bd11789408471e81eade74ab9f8fda2357f57bc870964 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/22.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/22.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..13ee44f9b9271463dfc32a424bd35ba85e7bae03 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73ec70212e3db491df066e5590c62ca5820e6f55e55261f798246b1467eaf826 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/22.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/22.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..912701f416d3ca66d168592b68b37c7e8389370a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:015d0ae0abee3e02618487b97cc1a77f453bac9421d6fddfca6a834ea0bf0327 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/22.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/22.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0fbd886491e0abac206961f890cfabd7d60643d2 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a35a3d2da326ec60146da7a49daf416558e81123187f191ebff69f2e2284ea +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/22.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/22.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1cd15071a3905a90edd55190b69967c2af7e7803 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd7baebc10709da149a709be3fded7819fc9d90b96d350a21dede4859740f56 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/22.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/22.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7b8683e48aca751259808adc1e1771e47271157 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:958279fc40ef4c4f2ca5da9d5b56dfc54494fbaaba642ca8b882909b851e17b7 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/22.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/22.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1e6702a9855c949e0b1a7bfe098e1f1ce6d9d519 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e809c63adf9e2cb7e1c64f8d4f1c9f7a2f3634d09b7605e63349cfb5a0ecc6c +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/22.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/22.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..90cb121f3b05192243b606eb69164258cb42b266 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/22.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e67db3928bd0a5eb21b1b89ae1566e9f6992313f3ac4616e7ea460514104327f +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/23.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/23.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..00a2294129aac0a0e78d6cfa648589733cbf74d0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01abf3ac3cab198277912ad2d6daa02a2b6a4038aa7c5143e8b60cbd2253ea42 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/23.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/23.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b54c620da9fa75bf5beec79f6b673c6377208208 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42404f2c36effb6c56c513fe274dc707a17948234dbba02d71807be7f88e43bf +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/23.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/23.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9119319e198c025f8acc40bd9406681fb4145e0b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db5a27819a9d64076e601a611fa86dfafa78b813163b1d99a902102c07cc79e9 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/23.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/23.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..966597994101c0c22393e7955073291393c2f87b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d443a6a9c92255e9edb6f7982295a77d4ce3a700d50557511b554c5e02d09e5 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/23.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/23.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..463e03e6aad4d8483a875f304c0aff5e4013bba0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eda82b7711ab2e38f32e496396f1c3b0d46a706ec965835e32a1f288c54c765 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/23.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/23.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ae7ce2936ac4fbbe018d55cc219eb46b02b5a325 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5ed54f8416fdda53509a3584e8fcf37279a659d7be3ae277c0f8b63d78018b1 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/23.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/23.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e170e66eecabe66c153989a8553b748e2dab9e5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/23.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3361fe3513e845dfeb38c6b9c6e38a8b945097e906b732e1cf92d63d966f80e +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/24.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/24.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5cee4eb17ed40a31e36d3f1cc7a65d98166b4a98 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9b7c7cb26ce252d64e6eda492b5872eac990ee15bc818617f854c364140576 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/24.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/24.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ba6f62ae736dfa9c9b5690bd733a6c11750a7dc3 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c48057743ab63ed393ecf6b5fee71878726b02c879b56ad510707b02479769d +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/24.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/24.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..05154e067cebe77ddbf5caef2c41a36b96b8c379 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ec2247d731e36bd26c6dbc9f82ca015e0c650ec9bed493b948242e47dfc329 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/24.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/24.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2235cbe43885bcb4df68fc823bfe55e7f8a66e66 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04613d22671afd99540d21ee6df6ae610d275068842f4b369a0015810865698b +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/24.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/24.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..20cf3460974e99b60fdf6e242cff8109ed563060 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e2f91a7d4fb35a237758dc4ac65d6d9f12eda604b594cef8cbc2c515bf9458 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/24.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/24.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9bdb53660a25ee970d270b9ab836c017b82deef6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d02a062f3f97e44cbdbb3e8b131cd3b60df5645704abbdd8eae19715857167 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/24.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/24.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b59100880a9a3affe7997680ada9a0a0fccc767c --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/24.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049ddd3f7c901dd8d7cfbf751617b1e3ac36a45eef178c22a6ad4f105f2f74a9 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/25.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/25.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..766ef9b4ffa09be611218947b683d4d68f0ad46b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5c0fa06eb4f50beb1321c86c98d81c9599c81ec7b3e0e9f22c16498757b3d6a +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/25.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/25.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4e3046ee84cd3a8f852cedf3532ad5326317fd8e --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c11868c96816d67dc0dfca7cb5e89c3ad06ef18390e67b2e75b645066eb4229 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/25.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/25.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c501498964d8fdbf67d1b22e4e6f6928bb37dc33 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15a3eabdc8ccd6b305df68dc15a0b61712ae21483ee619c1dd304112ef54f6bd +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/25.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/25.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7c8dc10b69be2120e874225e8ab7b789e7c63e91 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4dfe29ccda448f64e1de395462b2623e1892379ba9fad69e5da869017a7bac +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/25.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/25.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6fde0ec1680f8d4d026ab63c19575913adabf97f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0332993a91f35a6c6b68bbd0fc7b479fb3a1e08f95b651703a202492f196f6a +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/25.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/25.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..08982a97b4022dd69aaef885f341e6b80342376d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29727e977e25c40b96a347371c207c8bdb2e3ac659471be7711c5a739074763f +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/25.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/25.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dce776a0993058071c64f2e6c207defa1796957a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/25.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8993de7c8d060ad673a2786ae18662bb37f5ac6ec42c7eec258e0aa123028b2 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/26.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/26.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1164c6eab3c1b425b1bcb8b7fec698c55d528c7c --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b478379727b1f9f25d0441a85a6feccda74e96ceec7215be5ebbbe5776b3a6e +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/26.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/26.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e987d64ec9a2233f3e022d573d426765b522699 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0bedc900cbb6fbccff95e6afe9c7eadcdefa708933b75393933059521be1553 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/26.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/26.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..16fdb70bdaed5aaf26a56c37276db9c276cb764b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9fd93ef166bca418e282767b3c94bb41096b15aeca035bbbdd85b9aaa82ecc3 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/26.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/26.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d42db36c8b968a8aa4e57f45970444d41a318d12 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79633ba3b941d18b29653ce239e2e3c46745de918730d5a19ca66d86ead0b30 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/26.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/26.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6022e2e172875e590315fd97c5441bc03a30cab1 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f2e1a99304a2d1b024da8398313bc2cc80a08f56bf0fd2524318956ca0b152d +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/26.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/26.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..78105a94b87d6f5ee1c94627de4cc68b244833e9 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36cb1929ff2808b56ee127c5b20543e7671b6b9bd7c1d4a6c7add179cc175b67 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/26.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/26.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..395aaffbe1155771e73fb678612399772ac43a6f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/26.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:760c040ccb353b1b92ab3d5def7b9092af14e32ebd554efffe176ac3261d08d7 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/27.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/27.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..62258bccdb4e3b0ffa7e972024ac45c1776c0b2a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77e134587ce25ab634cd6e6d69fe611a199d837a12b3c71ab8a6916bbd834d77 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/27.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/27.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d1c3df839112f632df7c928b7117538910e2f11 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6ef54ada8cd8068df922f526f4d0aad9a6fbcb89bbec9f7d58df6290f8792d +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/27.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/27.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..be9b5465d5202d4d52d14e588ffd6bf53d9a640f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66dc21a34114b3f5ddf067bc4a4e42223ae6d32ec41445c44b95506a93d62f1f +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/27.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/27.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa95946d6d280e904644b04176151182da0cd112 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35f231b4870e87b81b4e7cb6d9ffcc6be1959881bec1321170f7e67e54a306d5 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/27.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/27.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..30503dd035ce1e08f76ac7639023a21881429f43 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a744d128f30e0a140f7a63dad31c7717b727d51ea076bc62810adbd578d3c0c7 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/27.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/27.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf9acc2fbd10283ef61ef1db3d21c252708fee02 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0d241e4b6b451bcf411a6e28c337bfa4d1ef6d32f0709988a347e9ba3df70fb +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/27.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/27.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dace6c2b7800d398c2042c9c306f8428ece491c8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/27.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5693406cc99c2f166340a56343e9ce9fdfbe5ba438131afa7d16ecaff65071ff +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/28.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/28.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6f0a30cbd860abbefb0ecd44713dd16b239e8fae --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b8a8d3596bf179e0fffdfe3295b0fc24ca329800da9043f01b7b807a98ecad7 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/28.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/28.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..10ac57b4bf5f9080ffde8bc3da28090ddad4f030 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b07221f971e36924bbf340c294d74d5f912dfa9426f1607575c5cc0afcc01e7 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/28.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/28.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d15f363e87597ebe16099d393e2dd540eec995a9 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6c1e8fadef0527f5c75e03da9d58b6e1e23c0811e73a944241bd9b14397f4e2 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/28.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/28.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ce36d6ac955e69febac625f85090a2fa2fe92ea6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0512337a9ce162de749c340aede049a2d212a849e74e993f3ede17f1831ffcb4 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/28.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/28.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..723bef6df983c52faf4c2789d1778a729d7e52cf --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d1a981710a6108c6b837c9017d4bf025ecd21658388c2008aacce41b1d08fdf +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/28.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/28.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a43444afc65d659b105f2c8ce6cdd353981bfe7 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b8e0ad20d29b26e1609ebd539670fcf59502ff1d0bf95cabdddda92dc532f67 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/28.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/28.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..95b03775fe2f547fb5c42f0bb45abc087c233e69 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/28.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe3a814fe2bae63458a402302a06dbe2de658a8ed570a71f74bf61add6682059 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/29.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/29.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..62d215b6afa15e00a4768eb89e9dffe45e2e64b1 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c495312f88847a722893cb8e15a005e88a299145cae2b48235095382b31343 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/29.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/29.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..dd769bda4dd060342cd3ca7a1526092332decb3d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1f8fa816b5d92fb34dd87d2dd378ff1b0908cde6c8f5d9b232812bb8c60c95 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/29.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/29.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..eb4506a54932e422b9473927be50f555e19cde4f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0520eea953ac67f22c69647fbdf95f3a5c7ae0a252bbed6dda941bce1e5cd627 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/29.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/29.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..61068a024ae578a3de0bb9e52913edac9317b8f9 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e41fc9efb5dfa343b250a4cf77bb31cf5f3a364fc6f5e8ccb3cbf4b25cceffa +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/29.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/29.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4a7d94f3ea8da834b953da02b7e091a549e71e37 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae498aa2891d30b8f2ed4050b6066aa521dcb50ffd97f146120fdd3ed24e5f35 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/29.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/29.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9603ea7e77289e8d9b59a30a030af201148077e9 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329d6db8aab51b2120a92feda228dd2c12be290c5587ddd82b0a43e641e72c64 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/29.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/29.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..347741c6e6d21433f772ca30be5a3f0ab6f017f5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/29.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b708c9db4870d04854e66a3c4d7073c7ca59e41e288a546126b7c19b1e267a7 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/3.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/3.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..501278820bf9d9cbe7c5b9a6c832e6dba3a65c27 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5db7f2650c2590f241cf1c17d4f7557aa2ff4937bca6ccf85a256e27e2bf69c +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/3.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/3.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1db59fbb05e2b42d420432f1a5cb8ea591e34297 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b384a62f61ffcf8aeb52b17f08d2d64282ef241594d69876cdf55136cf4bdfc +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/3.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/3.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..21b45b3b69353aea8cc7e140e6c450a3f84afb01 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b21600acc5a1da7995647494398c8a23181be7e409d265282267ed1a7233d70 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/3.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/3.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9541159e7d2c10eba7cca02ab7dcd7da28264d21 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df261db20b52f5e3f8a43b3631dfae32b664e2ec39ffab812cd83ab7f90bdeca +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/3.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/3.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5971fc7c8b8535aa0668c1e0f8392ef102bb07cc --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d48a41d04f3052c7e65f983b555c3a090e8bd56a50d3170d54db957ebcf5d8a +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/3.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/3.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4c23f80442c88f3ae1caba7f9cba34440b12779 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f18847bef1c3866f1f24652ac6b99f7cee9982f82dea1709ee4677127a74f68 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/3.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/3.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..45a1ccd9037782d3a9480e7ac62353845735d51a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/3.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae79aeeb787c75296d338e4d2add0f45220c1821bc1a18b945c803daf8dd2ca +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/30.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/30.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..35783c60c5d9fea008e4caafe2cd7ccee0e1048b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f7832b429a59989978325766d8a74de0f1d481668454fe7b1a4cb8301dd980 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/30.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/30.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ab5a82c3d6ecf4c81b8c3de9bc303e25c64d1c62 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e3ab1e5bac206e332eb3e06cc06cf9d62387cc6120ccb5628964b19f210907 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/30.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/30.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c934320787a512c650d68d2d4852f5b9a0c1bd44 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1303d3a304ad9779055e14e2b149f14ae307e376778321a9122ab6d6888796f7 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/30.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/30.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4ea6a877233479c119ce0b3b74601ef10300f25 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c9dfd5ba59d914513055b60c16bd8a10d9645b915c5780fd61adf13742a4fe8 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/30.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/30.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4418f9d09735c55a350e01817de6eea95d54b2b9 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c00f6d88c2806e21f6b842414f7ba7650353e13559f5a203f66a85aa0463a52 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/30.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/30.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a4ffb744fee1a29a72fa89913c4ca51bdc2e2df4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4754443fa961b47de2cbce18407ab223c28cda269292cc3cf20a8885aeaee396 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/30.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/30.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..16583999e73caaddc0921a8e33f63b9584a2d429 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/30.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eff21d5ef09759ec9d6bb6b1b9bc0fe3628b969609a97b3649ffe00444847aa +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/31.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/31.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..be430ef294a4c39d280c1ff4b273f6118533a99d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f725b896169cb84bfeb7a2f5d891c74a32928e7e50c00f883d79c744806d34 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/31.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/31.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..88fbe5deafb5073af5c6d563ac3e48b9131dcfc1 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5bde111a9b952d459133068270897e55fa74d10558923a4b7735d519c194c48 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/31.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/31.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4c07c82760e0f3127ab5b890a3a3d7bbfef1f44d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02de8ebcc785aaaa2a03f7165452ec1504a803f5dddfc55e93564743829a9e84 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/31.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/31.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..36b11a0fcd4f916b4eb71e18c5db425528319487 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b440d9d0e403cc1d27aeee3a774adb8a23fabdc4b32baae1ce38d04ee06fa8f3 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/31.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/31.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..245c79dd36f70a8fc33cfc0025c2848b625cadb0 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eccbd3a480911fbc7afe9100fdfeb8a768cc153d8ea406ef385caa25b03777f0 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/31.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/31.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f1ec8c8c677151d7a161b1b4bf1a10c40365b58 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39467ab04232c58efba163515ea836828b36024541d0c1aa6144762c44b55b37 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/31.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/31.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..927276ed94ee0a7478bc6d0ddd6d87f6a3e60197 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/31.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:006700c5136e47869cf1c03550c4d9ec0b74c9d6bb9f5d7889a25806ddb409f9 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/32.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/32.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3093393ef76f6d850bd955800aa7241f68899726 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba828958179c9e895feb27a88e57be4e91824ca39b9f95b22ce04b7681925af8 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/32.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/32.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7845101222b54689f9d432521c320fb6d2674bcd --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abbf52ece52db566965c7ec12b9ee9444043ddee510270f1f37068ed4e8c112 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/32.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/32.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a93e6ff13e9050e9c178c3c0b2918f88ba51cd2 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cffa805f672a9c66152c19fada8c7601fc16940b927a8c2cbcc1a276c4c0ee66 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/32.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/32.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1fa1de54fb10c87b7583846eb82b78d62a30cc8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c94374bf302e303da456c952568e9840a35034e0931bebdc3c9bd52503a104c8 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/32.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/32.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b5afe753195bd2174845a630d0883f826dc7609 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:951466ebb2fcf3d0745ed53a279f8d5e941dc1e7248480e876130bce30375b31 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/32.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/32.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..da472e99fe54c40689a3143934936701d37de508 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7790918e28ac0be6be6d2e4794c87606696880867efa5883b905cf56def4e3c9 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/32.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/32.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..5a2041f938721926e0619008471ec0aae0a806eb --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/32.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befeb5484ec6b96c839d8f44c2484ae5c9a3b4db607207402fb659e9fc12cca1 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/33.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/33.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..41c05cd079b7414d7ec8dfbf72793a8fe47dfe55 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06f75c66af1420776327f83e3a3b78c6cf86e4b69ceab9293a914911c569562 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/33.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/33.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..3d13f8780a11dd5ffd377e475a5e1012cb077648 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f38da824035e45c15d554cd87fed6084f20c34acac664d69e21f2456a04c38 +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/33.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/33.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..92af49925928fefb978eaf90d9ca8df5730294b8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e7d30c137e25d01c4be8a6efffdb3b10a4a578eab5a6e18ed2724665c19731 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/33.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/33.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ddac2521d16a30d8afa66c7e4bd8b344a7cd50b1 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26b4e3626bbde5ca6a12f613aaaff726a0746489858a82bebf5975c38ef134d +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/33.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/33.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a6189b2da50f6dd3230dd5fbd739d848ac992302 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5bc79e354bd7c1c0037dda8f4c8cbd1caf2c1c0030eca0b0209e056a3ec20f +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/33.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/33.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f524cf54c80b49dcdfdfc9113564b3fc12b8307d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f8bbb98fff6d35923bdabff1fb071311be8e517eee07b2ccfda00eb0004f127 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/33.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/33.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e62d9a72863967f53e66a1e3de4336fcecb53039 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/33.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ee6ecc9ee2ce266c1b5e0afd3c141dc694d7e0522b5feb399e03e8a5228e74 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/34.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/34.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..331b502ccb10ef21946508bb0a41dfc8f6dc577f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f311aa338a71be485470fb4d6d5df4ab42a1bdf0151db3b8209c27c7c3d38b44 +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/34.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/34.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..56c67574bdcb193eab94487b7788060a84a54345 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1917f0f9fac108b443f199c681d2a8c9a1c2e5fc271ac967c798188a6572405b +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/34.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/34.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..f3149f614183eb332b4cb714ec1ad0e019ec40ce --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe502a9bbc235d80fbefbe118c8192d8c20fe47f9fe4479b4813646ef626200 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/34.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/34.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a47bb0013bb9c2f9d11c56181f3c2475052b3b70 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ed812462783b5ecc728798bcdc7b5392ba2b20e2ff1a59780fd4877066a7e7 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/34.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/34.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b4160f1a14ec4426bdcd09dc451fde6f2a3ef1d3 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e2735d288475dc757530adcf869229384fb5fefcd55ae479c17d56e796261fd +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/34.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/34.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..62ef494170883906082932cc7cfc47f19171cddf --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2d18be2b494b9aaaaef6c613fe9e23e230f24387ad6f32cd6e7e21e21317ce5 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/34.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/34.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fbf59f92d8e66ce4db493482a055db366deb691a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/34.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:052ea1a6d2e02aaf23af70e68b3404b5d5a23032ceefdd64f959adf81a136c58 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/35.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/35.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..229b3593e7a99beb8f38954d373956c44e46d000 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27d56014b17aec1f60f0e8944260d4e14048826512257a54d618bdddfad90a0f +size 102609831 diff --git a/checkpoints/Qwen3-8B-Base/35.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/35.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fe31420e9d4175176ddb96d6f0083b57393beefb --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f20d8eb3c24cc398235ffe1cd052b7693391736a0e65e86eef1f171ece56f17c +size 102364071 diff --git a/checkpoints/Qwen3-8B-Base/35.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/35.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..16f5345c2fcfb7650d06b45614f8166bda2ee035 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79f6ae9f551d2851118ec9cf8ef20b533b71509577763cb075e138f54b4284a5 +size 102364033 diff --git a/checkpoints/Qwen3-8B-Base/35.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/35.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0110c122f4f61135bfe187c9e1961e90bbdf815c --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f306b2a1245a1ef10d7a200a2f398749140cb7c3e5c060a939744a880f7db20b +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/35.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/35.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..ece5ba5ad3e8c2a11b79b18841bace79a09925d4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341ca2861ade130d42b7fe8074ab4360224fa23b72b0a4fae88907c03cbb9d87 +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/35.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/35.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..9d21df3b62c41647a80829e8095cda1f9182c32b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c4faf91d02bd186fff3737de2d4ba24cb27ed09c84f3dd1bd0df5eaf8af55e +size 34206688 diff --git a/checkpoints/Qwen3-8B-Base/35.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/35.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1cb52d10ed88a754b636009f85625807915b827 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/35.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b112fd09d12ce1461faa3605b1d655e5c950dcbceaf290d510a8fe285e26c630 +size 8647648 diff --git a/checkpoints/Qwen3-8B-Base/4.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/4.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..d2afeba0226c5e35f11fa1b0945681130d12e20b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef91de262e70ae66e82276677e0c584357bfd5e8ddf9c44d84905e909b9b3b1 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/4.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/4.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..247540471289d72794fadd8a5dc79264bc2495c4 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8afcaefc46bb1f77a2970b78581f73479c7588e65c86ce46cca2b63016de0498 +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/4.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/4.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..de7e166e595ae3be50e6d1837d763117369d292d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e275e1e79e1535ee2bbd0d94387809d99a69ff5dcbe3cc3b703a230b82636f7 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/4.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/4.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..cba60e6eeed73f9bfe045ab1901f14fd8dca30d8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c2ca53963e0f6345749dc11ed40d0c75d32b48536309a996cd39e747972f87e +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/4.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/4.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b9c8c6c262948797280baf4a6c79761ab836b3e --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f136dc35c2ebbd5824a37355aecb0dbad378fc112696e80742283335a0c781d +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/4.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/4.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..450280af81549d3bd32bc2ce83c62dab36fb1a49 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8439f2b28b4c923451c0e940e162deb8b83ecbd17ca622e5ae56954384cbf977 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/4.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/4.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..80d439682ccaab4bc50b757a89c02cf4160a416b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/4.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c211d31d27c8ed102a98a18d95ae6c7c05d1a9a77489c9e46bd891163c46b9 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/5.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/5.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..e68ebe50c99755ddaefa5744d9b064d71bc1b052 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e668554b6f39aaa95ff9a536e1f52ca4a114e0adc3e407a81ad058210e50f353 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/5.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/5.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a6ae706a331316798fe9fa36eb8edfbdc3d63eb6 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da3063f81bb5e7f159c172ed24b5431201d292b4f5a81b7da89620412fe1fbe +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/5.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/5.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fdff022fc81050233a96eb7d1185e32be7fa57f8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e8bfc47adc39bf076b12deba651b6b4d23b591cc77c4badd6ef759ed130b3b +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/5.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/5.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..db1620e2e7ca6215bac4c89643cf134ac09f2a51 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e802f3dc6211e2c2bf2563d7b734add4812a59509c455331c31355fe62f992ae +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/5.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/5.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a8e3d4df6bd1de38c164a3a7a7033ae028546631 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5afc09a74b80449af4a1a0f29be3bfbf97ac2168477a096edbafef71814ceb9 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/5.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/5.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..68c0696100a9e42f05132870b6b7519bea723666 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd86dbcefc6c7ec5c345faa6fcfac71fa005e7d3ba01f4d35340e3761841927 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/5.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/5.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c41a968b2db9bd2228cc0c7d2110924c6d1d2c9d --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/5.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a236ace28cea876aec1788e6fc1235398966e9da47a32650d0ec4c6fabfe1c7 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/6.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/6.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc66ca8d9792e077e4dbd39f8c1264842092587e --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54d14d3c8e8efdea747fc687d643c8c0764fc986344f15f9be370163fde2e800 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/6.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/6.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc79577fd648296e04c87f864fb1f59babe8e551 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bfc527ffd2654c28c02e21f481186ac3b8226f2dbd30e61f868a7f09cf6d42a +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/6.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/6.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..355e24875793fd9ee87bb5d5c4bfdbd250820d5f --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9f957b96763c6a1498c7c434be5019ea919e5affcfd24fef64f4128f28358f6 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/6.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/6.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..464cf3beab97810ec1761091f2421fe8ba2ce8f5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c28e3f37ee2b905e46bd850e047fde6313b2181d039e494802b395f7d54bf8d +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/6.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/6.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..718faab992f6ba739db12851c308f0a88969aa55 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae43f98b21ea14f8ca22b26224d4ac0d34d6ed597fa484923dac05b9b974d14 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/6.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/6.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..32ceb40225be3390ed26a67fc2ddd36ba1aff130 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634aead717ac6cb40dee8823df9046747515c049bc7340dfb9410357b499f15e +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/6.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/6.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1d18a62a74fbe1d166b370aedcb224083119a098 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/6.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6890e02509b3647b3a48022dae3b99b3592f1d106d82c1214271c73bc80b19 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/7.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/7.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2110a1dd5bc7e4b4f709b676089dbdf7bcec23fa --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b92622a03502fffd4cae29d6c217dd4776ea7c5248d6a2dc501e6b7b1709130a +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/7.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/7.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..1373b45ccc8f67a3ba231c6b56c2531f6691c8ad --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6b7fbc67f3ecbe79434f45aa1e666a7ca87e8696ef6af9744c78d18ee6ca37 +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/7.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/7.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a79b04ebb67250e47ee5297266daabb3f9999f0a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c4f1a992b59e4ca6a2e8facbb1b931a61ab7439d8a5f83903ed5ad55b28c161 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/7.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/7.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e3e620af5a71de52da44c090337ee142b9c5e96 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f581ab8de738abca553c9777c1ea6f77d98a7bec1f741950853e3efe5c8060 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/7.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/7.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..de1ce9c3c4b438e050d9a4a65132fc75b61938d5 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb7daf34a7f609d84d319fbcbaac3ca51bd02107f7eff6980f66a191d3431a83 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/7.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/7.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c06f1abfcfd064ea3dcb174579cc32d33d65fae2 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25f58bad55a9eb361baee0996707a08776dd828494de080ac26b0656792ca2cb +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/7.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/7.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5cdc6dd8c66da2b0a44cb16ab0cea97a5c603b8 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/7.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77eb86a37cb3a7975ba51f7072738a7b5dbb579c7c6c463edd862e5d4c394c36 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/8.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/8.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d29c8448f661b1bf0221d788d12a40518196e4e --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033183818c220ab726e9c905d09e1bec57d3dc65577c6c2571b8e0fa40cd3172 +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/8.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/8.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..efd5e1cd0f3778678488220d7ef8ee963912d215 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbde273f1d9b40cc17447344aee2bfbc009ccb8d3d48967a5dc5aaf9f9c0e698 +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/8.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/8.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..62aa80e770a17be5f8b07b3463f7a6da2f90880b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b31f16e47ed02e7d2108ee7e4703b2dbba161c5458ea38b1949dd53ea5f1a456 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/8.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/8.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..7d092296f6dedb7b4007faaed3853e515e9f657b --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798d70ee94e8b011f53a91a9e34760ba3276278e1cdf73824f9a8c62e886488c +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/8.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/8.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..568a33d11ff04750c89b1fbc1ef9d4641b1a4310 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1aa4c7ae1970c74484b579ad1975e3e513264f9ee34031f95f6aa02d2b1a765 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/8.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/8.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..c5123d950aa2d740f545da474e448a24e92af847 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88aae5d10b564c0007ce3d1c91bde3afd48e41fdd4de1616826eb505b45b55a3 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/8.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/8.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..b47daca7891d67e0ea8e5fe0cee148faaab17172 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/8.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df35124e5fcb83922f19d91880865e2216226ccd4ea33face48a1af2867d4f5b +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/9.mlp.down_proj.pt b/checkpoints/Qwen3-8B-Base/9.mlp.down_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..25ac8806d6382e50b633d19887bd94dbe646adc1 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.mlp.down_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa092d131002fab38a1d99be857056a1d1e7344e8fe64973c06b6e7ec8557ad +size 102609812 diff --git a/checkpoints/Qwen3-8B-Base/9.mlp.gate_proj.pt b/checkpoints/Qwen3-8B-Base/9.mlp.gate_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..47f2b56b6b38ea0ae5894fb602dfe5402a10de4a --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.mlp.gate_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea647a94a2ffdce70ca372da6e0f6cc43ee61e6acd7ed5f088edaf466fe9110 +size 102364052 diff --git a/checkpoints/Qwen3-8B-Base/9.mlp.up_proj.pt b/checkpoints/Qwen3-8B-Base/9.mlp.up_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..abb274d4a989b4e83d890b1ce59a19864f88c737 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.mlp.up_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456ea3ca98456caa476a0f0741850125f7076ddf2c5aa446972a279ab28080a0 +size 102364014 diff --git a/checkpoints/Qwen3-8B-Base/9.self_attn.k_proj.pt b/checkpoints/Qwen3-8B-Base/9.self_attn.k_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc5df1dc43affefc629adb32f13502063ce7f275 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.self_attn.k_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a307a5313c8dc21c26c8a3065fb2ee5383bab895edbf644803493ca73b82deae +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/9.self_attn.o_proj.pt b/checkpoints/Qwen3-8B-Base/9.self_attn.o_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1f6922cfbbf54b1ff3242ace73e2a122c544565 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.self_attn.o_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5762ff93d7aaf933c98ab4df92b4a41ee8637a86fb13c4227eee50f05a538c27 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/9.self_attn.q_proj.pt b/checkpoints/Qwen3-8B-Base/9.self_attn.q_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..6efd31424dca060e73574b1d9f1a12a47d908bbe --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.self_attn.q_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cefc0ac2629f95c77b7f2ac77e27eaba36503ec24ac55d0f14cdbf4db8754a7 +size 34206669 diff --git a/checkpoints/Qwen3-8B-Base/9.self_attn.v_proj.pt b/checkpoints/Qwen3-8B-Base/9.self_attn.v_proj.pt new file mode 100644 index 0000000000000000000000000000000000000000..2dfaf9c9d81870e81674b98d08512b27dd586ffa --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/9.self_attn.v_proj.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3607fac3ea99ac63f872f973a5dae454727b57e042b28a631d9d650701ded73 +size 8647629 diff --git a/checkpoints/Qwen3-8B-Base/args.json b/checkpoints/Qwen3-8B-Base/args.json new file mode 100644 index 0000000000000000000000000000000000000000..7492a4f4bbc003ba9997cc05050f77fba02f5717 --- /dev/null +++ b/checkpoints/Qwen3-8B-Base/args.json @@ -0,0 +1,45 @@ +{ + "model": "Qwen/Qwen3-8B-Base", + "epochs_list": [ + 10, + 10 + ], + "early_stop": null, + "weight_decay": 0.01, + "betas": [ + 0.9, + 0.95 + ], + "eps": 1e-10, + "loss": "smooth_l1", + "q_group_size": 128, + "n_bit": 4, + "params_to_optimize": "channel_scales:0.05,angles:0.05;weight:1e-5,quantizer:1e-6", + "use_scheduler": "True;True", + "sched_freq": "step", + "datasets": [ + "wikitext2", + "c4", + "redpajama" + ], + "val_dataset": "pileval", + "train_size": 2048, + "validation_size": 64, + "batch_size": 16, + "seqlen": 2048, + "seed": 0, + "use_og_input": false, + "shards": 8, + "results_dir": null, + "resume": true, + "layers": "all", + "output_dir": "./output/random-pairs", + "init_rotation_params": true, + "num_rotations": 8, + "num_pairs_factor": 0.5, + "use_kernel": true, + "checkpointing": false, + "reverse_pairs": false, + "random_pairs": true, + "first_n_layers": null +} \ No newline at end of file