diff --git a/config.json b/config.json index 68b5a1596e61ef956c5276d7bfeeb7f622001fb4..991ed333fb0f06feddc79503a53be03d3f414d4f 100644 --- a/config.json +++ b/config.json @@ -127,6 +127,46 @@ "bits": 4, "data_type": "int", "extra_config": { + ".*eh_proj.*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.0\\..*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.0\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.1\\..*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.1\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.2\\..*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.2\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*self_attn.*": { + "bits": 16, + "data_type": "float" + }, + ".*shared_experts.*": { + "bits": 16, + "data_type": "float" + }, + ".*weights_proj.*": { + "bits": 16, + "data_type": "float" + }, "model.layers.0.mlp.down_proj": { "bits": 16, "data_type": "float" @@ -3558,13 +3598,68 @@ "model.layers.9.self_attn.q_b_proj": { "bits": 16, "data_type": "float" + }, + "model.layers.78.eh_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.mlp.gate": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.mlp.shared_experts.down_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.mlp.shared_experts.gate_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.mlp.shared_experts.up_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.indexer.weights_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.indexer.wk": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.indexer.wq_b": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.kv_a_proj_with_mqa": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.kv_b_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.o_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.q_a_proj": { + "bits": 16, + "data_type": "fp" + }, + "model.layers.78.self_attn.q_b_proj": { + "bits": 16, + "data_type": "fp" } }, - "group_size": 128, + "group_size": 64, "iters": 0, - "packing_format": "auto_round:auto_awq", + "packing_format": "auto_round:auto_gptq", "quant_method": "auto-round", - "sym": false + "sym": true, + "block_name_to_quantize": [ + "model.layers" + ] }, "rms_norm_eps": 1e-05, "rope_interleave": true, @@ -3577,9 +3672,8 @@ "tie_word_embeddings": false, "topk_group": 1, "topk_method": "noaux_tc", - "transformers_version": "5.2.0", + "transformers_version": "5.3.0.dev0", "use_cache": true, "v_head_dim": 256, - "vocab_size": 154880, - "torch_dtype": "float16" + "vocab_size": 154880 } \ No newline at end of file diff --git a/generation_config.json b/generation_config.json index cdf918d86b3f8523b2c90510aee4205bc5cdac35..4bea9e4576fcf04f9606430bc971cde4716c5351 100644 --- a/generation_config.json +++ b/generation_config.json @@ -9,5 +9,5 @@ "pad_token_id": 154820, "temperature": 1.0, "top_p": 0.95, - "transformers_version": "5.2.0" + "transformers_version": "5.3.0.dev0" } diff --git a/model-00001-of-00081.safetensors b/model-00001-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ffe4056ad24bea1262167e362d73a83e8334d492 --- /dev/null +++ b/model-00001-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1197f76af0e5fd34095f0b153d6e47a3525c2e930b0e7d01e832f33e43c1eb +size 5365774416 diff --git a/model-00002-of-00081.safetensors b/model-00002-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e6b32f43b6460835ea978c84b5ca3a804aae6f9 --- /dev/null +++ b/model-00002-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a875080d271a6b6003e08afba16a0e5a2df25fdc7cfdc7229d150c6a2a7da08 +size 5365732064 diff --git a/model-00003-of-00081.safetensors b/model-00003-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0ad253dab6b072ea54b78cd84db07d6be7f6b3b --- /dev/null +++ b/model-00003-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36f352b0159aa275fb4eb17df8d77e79ebff249d8eaa8e687d597252a43a798 +size 5365732064 diff --git a/model-00004-of-00081.safetensors b/model-00004-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc894db01e7601cfb03bc754f3acc48c4101c54d --- /dev/null +++ b/model-00004-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8b576ba3a07b265a7e05b6087ba43f5f15580908515d0722300e20a8bf4159 +size 5365732176 diff --git a/model-00005-of-00081.safetensors b/model-00005-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b30c44077911bf5298ba3462474e83026c95e086 --- /dev/null +++ b/model-00005-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed86fb47c3d25d5ed87a703f28a8d45623d1c0e9039e0cb404732a7a6e63b30 +size 5365732184 diff --git a/model-00006-of-00081.safetensors b/model-00006-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbd2b137f2e08d00d0f6ef765246b52ae618daa7 --- /dev/null +++ b/model-00006-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9657cc99336c9cbffb10648930f4b6b3c8368abdb80e630f346ce86f4d00e865 +size 5365732184 diff --git a/model-00007-of-00081.safetensors b/model-00007-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ebe5d869728b80c0c5a287f5823dd0a8d38dcb2 --- /dev/null +++ b/model-00007-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:407ef6771d1e40a5af4057a59a5bade69e088a891f38b1fcc96eb42e743ca869 +size 5365732184 diff --git a/model-00008-of-00081.safetensors b/model-00008-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ecafb8312150ef5da7b703bade075ceb0f569c43 --- /dev/null +++ b/model-00008-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cf6cec1630e08d520fd178ad4129d7aebea8467e8a704a453104e75e0047b7 +size 5365732512 diff --git a/model-00009-of-00081.safetensors b/model-00009-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f3dc735ea7995f9c5265ba530e8dc258240c1f9 --- /dev/null +++ b/model-00009-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:481455a5aae7805dbaad86bb79d7fc2e4eac70b03b5872d06c4ca3ab99392660 +size 5365734384 diff --git a/model-00010-of-00081.safetensors b/model-00010-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e064f97ae68777bd1f5790bcc4d8765861e70e6 --- /dev/null +++ b/model-00010-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa4553377afdabdde9e77666b91b83943f54489b1c435580d5f0393ac04f592 +size 5365734408 diff --git a/model-00011-of-00081.safetensors b/model-00011-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6087746f70c5a0f00657da2a9d7803f32460f3f7 --- /dev/null +++ b/model-00011-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d22ed9a62d1dcd851c71439bda774f498801a1b42b6092e4fb5486ffbee78247 +size 5247413488 diff --git a/model-00012-of-00081.safetensors b/model-00012-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..275222f7c87781241f5a92c80a1ab6b9288e4e1f --- /dev/null +++ b/model-00012-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02cbc14536522d7235f142ee5a97cc245ea818de5aa3578bcec6d1bd9aebf500 +size 5368629832 diff --git a/model-00013-of-00081.safetensors b/model-00013-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..07ffb66dc3feda2851cb82adf3203e08089a048e --- /dev/null +++ b/model-00013-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2517b5b27952713b1246f384a284649a4962d2ef36c4cb6e53d7a2d63c068d +size 5365734264 diff --git a/model-00014-of-00081.safetensors b/model-00014-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..da77550fb8e38b79a8eeb9f438102903d3b384f2 --- /dev/null +++ b/model-00014-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5196a9def170211598f323aa923f83ab414e4228d33170b3bb771fb1560efa08 +size 5365734272 diff --git a/model-00015-of-00081.safetensors b/model-00015-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e6779aa0c048afcbe4d07a713f609b0d61669925 --- /dev/null +++ b/model-00015-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d48e4452e95de54f7d8d9685ee3e17f9e6d6dd835c4308c4854b08100285216f +size 5365734264 diff --git a/model-00016-of-00081.safetensors b/model-00016-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b44bd8a79d13339f2cff573cb154932424098ef --- /dev/null +++ b/model-00016-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e018b0661f1c5c8ea1ff1844391e1e173d8f7d557aa04a396446624975d255ae +size 5365734264 diff --git a/model-00017-of-00081.safetensors b/model-00017-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8e5991dca4bac4bf1f4fd522584728da24b147c2 --- /dev/null +++ b/model-00017-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cadadb60928c58a524319fe1302e6aa4c8a0b9b42b40984193fd4944ff0d8ecc +size 5365734272 diff --git a/model-00018-of-00081.safetensors b/model-00018-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca5bee9ef0444252e0f139defe024594b753786b --- /dev/null +++ b/model-00018-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:095945ddf50b9d2937836b60e3ef92fd08543f0136166c0ec422eccdb5636c29 +size 5365734264 diff --git a/model-00019-of-00081.safetensors b/model-00019-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..647ffa1df7bf62d5074e05413bc00fb560e9e866 --- /dev/null +++ b/model-00019-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84e5ab9d0b63c9350dab81fac7126d49ecd3ce0177700c96671d0d80028efee7 +size 5365734264 diff --git a/model-00020-of-00081.safetensors b/model-00020-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4e1146c1c9b1b70e6b8b3e54b04999aecf1fc6f --- /dev/null +++ b/model-00020-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bcb8ad254d324e0a498a972a5db9ab445c46e6b52f6e64904e9beac4b91c8ed +size 5365734272 diff --git a/model-00021-of-00081.safetensors b/model-00021-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b9ae85483d29129322789161477c9e01b5e378c --- /dev/null +++ b/model-00021-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b2b1f19b9692b4711f8ea347bf36f6b18d8e5c9d2d39461a46be80534d796a1 +size 5365734264 diff --git a/model-00022-of-00081.safetensors b/model-00022-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cf0455ee82e84f23701085367a5801dceb81ff0 --- /dev/null +++ b/model-00022-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69db1f9ca66783117f9bdf6adb4a03c884844be732a090f2e2aad874e574b13 +size 5365734264 diff --git a/model-00023-of-00081.safetensors b/model-00023-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..78c7d0ae7e804e6d85a3c33ad0eec9437a62115c --- /dev/null +++ b/model-00023-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7b19612e7c89ce57921fd953321656facf7e3996f75f7065d94f67b1c970807 +size 5365734272 diff --git a/model-00024-of-00081.safetensors b/model-00024-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..350279892d22238e7626025b0bee31c994510e38 --- /dev/null +++ b/model-00024-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4747b09af8ba3f5a695286084e66b2c2a208a12f71e6b6e61a9cbdb8889c8f +size 5365734328 diff --git a/model-00025-of-00081.safetensors b/model-00025-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0abe4bffe81338fb272c00a8606852092e427f3e --- /dev/null +++ b/model-00025-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132af142adbdbe086481faa380772ed7eeb2d7ba4bc2ef1e8aacc9aaeeef12f9 +size 5365734384 diff --git a/model-00026-of-00081.safetensors b/model-00026-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7635e2d66fd51c0d8e1267d0dec245fe778fdad6 --- /dev/null +++ b/model-00026-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f46738a8455d686053125a094abea1cce28b3ccb921f742fb36fc563faf28d9 +size 5365734392 diff --git a/model-00027-of-00081.safetensors b/model-00027-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acdd117f2fcd3b571f91fec2ce3f96c4cb4386ee --- /dev/null +++ b/model-00027-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee2e736e2a7e363acf251d39b152ac3c112d599ec48db7900c77c33c4893306 +size 5365734384 diff --git a/model-00028-of-00081.safetensors b/model-00028-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9071a6a05f6a0182af2fb24a78ca42695dd765ed --- /dev/null +++ b/model-00028-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af9571bb77313fcb776b1c77072612031ec0e1f88f0f82584a0a7b067c1b5db +size 5365734384 diff --git a/model-00029-of-00081.safetensors b/model-00029-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6f65e76beca247c35be10601eabb8cc4b30931e9 --- /dev/null +++ b/model-00029-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e66bd83cd3516fa2668ba75b1dd4ea0967462e49980f498eba0b0e8b3bdd8d9 +size 5365734392 diff --git a/model-00030-of-00081.safetensors b/model-00030-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ec63858cff4fabe3188c88e493dce26b8a1fad6a --- /dev/null +++ b/model-00030-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bed9157d14e0929091724310acb5fa425872a9bf284b8e631bab64914cb092b7 +size 5365734384 diff --git a/model-00031-of-00081.safetensors b/model-00031-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2bc5464a870876e307233ab6699476cb4da1d23 --- /dev/null +++ b/model-00031-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7781dc5078ea16211d93dd3b135599d921c8cb96c00a581636571df9526769ff +size 5353773400 diff --git a/model-00032-of-00081.safetensors b/model-00032-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f37fcde8251ff4f314732a4c8b0cbb174d0c67f1 --- /dev/null +++ b/model-00032-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f7dae429fb50432dce3553a509a6b913e656381923c64f0c051ab63c1d8bac +size 5332193040 diff --git a/model-00033-of-00081.safetensors b/model-00033-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d50126dab4fcd497de9523c45addaf8e90a96db --- /dev/null +++ b/model-00033-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:906e71bf3dae86967f335cd9d9e3d7828889caa172598b7904500ca53ca8637b +size 5363644672 diff --git a/model-00034-of-00081.safetensors b/model-00034-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc8c5c7072669c98c769f3fba782d560ce01dd97 --- /dev/null +++ b/model-00034-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:700543c4c04007998ed780a0fb7a180b31c3aa2cf07c4597b522200e71731641 +size 5365734272 diff --git a/model-00035-of-00081.safetensors b/model-00035-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4d913cb2eb5d39d062d7e3c3a04cd3b4ace5341 --- /dev/null +++ b/model-00035-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de6f4de39ee2a87bc8c53fa7c26c174e0d3f6885ff87e477e9e60e3599bfa470 +size 5365734264 diff --git a/model-00036-of-00081.safetensors b/model-00036-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23ee66550355902e1368d8f5361de6f9b0aaab5b --- /dev/null +++ b/model-00036-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4eb2b296871f379c44de0672a415d164a9129ffb524f49a3cb3e4f26f483d9a +size 5365734264 diff --git a/model-00037-of-00081.safetensors b/model-00037-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b07130e36c82ad274a492db11e0217c67382f20 --- /dev/null +++ b/model-00037-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87d6781f20faad84abf1ed77ee33d9234ad5b96cebe8b84dccf57e1f6718edf +size 5365734272 diff --git a/model-00038-of-00081.safetensors b/model-00038-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4f305998b149a2cd2826642290101ea928ea3c1 --- /dev/null +++ b/model-00038-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed80736864bb9a38b49fd6127723b228009dcf175970cef47d467b34df500f57 +size 5365734264 diff --git a/model-00039-of-00081.safetensors b/model-00039-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2283d2ce5978ce660f23942f3a26564715c02438 --- /dev/null +++ b/model-00039-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f059915249a7e061f288b826ea8acf8e9d9fa087b3794a337e7b7f7631cb76 +size 5365734264 diff --git a/model-00040-of-00081.safetensors b/model-00040-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5bedd03b01716970753bcb77d41e60cefde5ffd0 --- /dev/null +++ b/model-00040-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4a1eb05f400c4135d61a19c87b59485542430854cb831fcfc322b06ca316c2d +size 5365734272 diff --git a/model-00041-of-00081.safetensors b/model-00041-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b7e1a3145126b8f0a3d3f2fe3d265f1c5f3e09bf --- /dev/null +++ b/model-00041-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c76b5ceff7eaf533cf721dd97856da249ffe168fd54a99a6c20fd8e4d126fd4 +size 5365734264 diff --git a/model-00042-of-00081.safetensors b/model-00042-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7556788dd8f374814e112b8d359d1ee03c27baf3 --- /dev/null +++ b/model-00042-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b57a502c3592e168c309fc5b6e0f787941bdff864bc75868f0d493c7e738698 +size 5365734264 diff --git a/model-00043-of-00081.safetensors b/model-00043-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe96b4b2b9eecb698a9df210062c35b2f3c088c3 --- /dev/null +++ b/model-00043-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee21f944255d4455d4e02332354bc0efcbb7461361bc14a11444f875251dc1c +size 5365734272 diff --git a/model-00044-of-00081.safetensors b/model-00044-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7621c132c205190de62be4415f3eae63d1adb1ed --- /dev/null +++ b/model-00044-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0196043da7c8f0f4b0866f0f468c7761173478ce7a05ccf8dade9fece015cfd4 +size 5365734264 diff --git a/model-00045-of-00081.safetensors b/model-00045-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82b4b960b0995838d3a0e1f13c312b0396c5e829 --- /dev/null +++ b/model-00045-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2a41faef0a5ca06066ebef886bec281a055a13a761608d78af997dbc607513 +size 5365734376 diff --git a/model-00046-of-00081.safetensors b/model-00046-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..98712f558d33f1a72287c1c91048cbcbd7e9c95a --- /dev/null +++ b/model-00046-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:194cf50429e9d0b2300f0a8637e68312ec73b04fd50ea116eb8b44113f148c25 +size 5365734392 diff --git a/model-00047-of-00081.safetensors b/model-00047-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ab0e0aebe71f12febff2c9ff68003465c442631 --- /dev/null +++ b/model-00047-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a73a340ec8e3d9d5b0603aa35bb060ebba01be201d521bbd4883a079449ef34 +size 5365734384 diff --git a/model-00048-of-00081.safetensors b/model-00048-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4afd715e6ebe293ec09a35b2e1bb6579334ee031 --- /dev/null +++ b/model-00048-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19be82586dcc749e19ede28423b4ead8cfe2249964c0e9df04698a9d7b27510a +size 5365734384 diff --git a/model-00049-of-00081.safetensors b/model-00049-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5b8264d2b36f9ab4f8bf7eec8027bcc454e57a3f --- /dev/null +++ b/model-00049-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebf81590c53483d5e6e4a4ca85e28a6afee2ee8c64f1bffa8399a5d2fa4e8760 +size 5365734392 diff --git a/model-00050-of-00081.safetensors b/model-00050-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b0bf69a522071b4caa15920a35bff3c7b7f5809 --- /dev/null +++ b/model-00050-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6bd7be68e430cad39edaae16ca3bfd1f6ef990ca94218512e41cc08185a45dd +size 5365734384 diff --git a/model-00051-of-00081.safetensors b/model-00051-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..74c624abc20b10f46c2578ea47cd53cc1e18800c --- /dev/null +++ b/model-00051-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0749c992118ec7ae9545df0761d6cd21cb86457503e8802241eabbdf4de6c3ce +size 5365734408 diff --git a/model-00052-of-00081.safetensors b/model-00052-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b91a25b04357a60b6f1e51aaf8dbfcd8a1569ac --- /dev/null +++ b/model-00052-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e244141e81da73594c569c84f8298db556abb098d54a1d430b9d2e4ad52d8dc0 +size 5260980176 diff --git a/model-00053-of-00081.safetensors b/model-00053-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..56b441ad754603e7e702c363d9e05435badc6c67 --- /dev/null +++ b/model-00053-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d76b4344e340ab613a4dbaeb124956b9489c356516d3add515f43d91fa16d81 +size 5368629832 diff --git a/model-00054-of-00081.safetensors b/model-00054-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1bbd40bcc1eb8ae768bae326db5a9614f9204169 --- /dev/null +++ b/model-00054-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7adfbb2bf316e887fb2902d4e7691698b4780044d8e16d4586c2d3492cf8982f +size 5365734264 diff --git a/model-00055-of-00081.safetensors b/model-00055-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d15720954d2d522dcce23600fbd1503e05c80614 --- /dev/null +++ b/model-00055-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d481335001c1925b62719d4b05cea64f8982f06c09614e841c2ccd566bf2eb0a +size 5365734272 diff --git a/model-00056-of-00081.safetensors b/model-00056-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5864dc9740c01f84c697afe3f46a9e7486b8abdf --- /dev/null +++ b/model-00056-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca21beea7e55aea2025980be83dac541f3d6ceff95aba234abfd8cce7789fc48 +size 5365734264 diff --git a/model-00057-of-00081.safetensors b/model-00057-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ba3d6e5021ca0c78ce9f971b0880816abcaf57bf --- /dev/null +++ b/model-00057-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5a883a3996e91c7ca0860405e46d146ab36fa68500c3f51a848e05e435c83a +size 5365734264 diff --git a/model-00058-of-00081.safetensors b/model-00058-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e13e2e9aeaab621257c0fbff13264eb0b716272 --- /dev/null +++ b/model-00058-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a9a056f20f93184d1c0a140f62df7fdb20f41225c55348bc1bf5ebb765d8a5 +size 5365734272 diff --git a/model-00059-of-00081.safetensors b/model-00059-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..50bc48d17a62c103441b7a522677c4022669f14f --- /dev/null +++ b/model-00059-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5022899d873110093cf00bfcca0e12ed03c8dd0a1a4c2d94c2b7ae3373457d +size 5365734264 diff --git a/model-00060-of-00081.safetensors b/model-00060-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16e73b4f755bc641e1b361d292d24a424d5f76fd --- /dev/null +++ b/model-00060-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a6e7152fbbba218dacbf3bd5aa90cb6e94045f22d544aebf4b1e4ac12707fc +size 5365734264 diff --git a/model-00061-of-00081.safetensors b/model-00061-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8b26204271fb98f17523596db3b610f697d04cf --- /dev/null +++ b/model-00061-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05e3e470a0dded805a6fbbe2088c2e5343e25abe8e4d2f078e371d34455d125a +size 5365734272 diff --git a/model-00062-of-00081.safetensors b/model-00062-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95a568cf5ba8da773d51da35d2345f90dbd6995f --- /dev/null +++ b/model-00062-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d62d59ee5c6a87b19cd4356c88e7e5ad750975155f5353ad7b3c9a4022d8474 +size 5365734264 diff --git a/model-00063-of-00081.safetensors b/model-00063-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f6a9ef989146c3dcbd63c6d8e933b97856ad49b --- /dev/null +++ b/model-00063-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e4c442fbac26984739dba2f337f29822decbc27eec303ab21ea59984d8ea740 +size 5365734264 diff --git a/model-00064-of-00081.safetensors b/model-00064-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8814ebf469d4827ed34b53c51e64968f0f7a18eb --- /dev/null +++ b/model-00064-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad6ea6f168b4bb4a069d669dedf167d7f7d8e10e7ac1f230d53470cd87b1a0c +size 5365734272 diff --git a/model-00065-of-00081.safetensors b/model-00065-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa73fceeedf2ee10c89f5e515b5c42312aa0d4e8 --- /dev/null +++ b/model-00065-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d1c05f254e7d1b0104b35e5e0dc95bc78c6aa3401a98399378bcb9df635b557 +size 5365734328 diff --git a/model-00066-of-00081.safetensors b/model-00066-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6bfc605d7673d87fdb462401da1760f40b97fee6 --- /dev/null +++ b/model-00066-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797a4d217958329cb4350c9d8f6abf92710ee808387b332a7c59b3ab2ed2c358 +size 5365734384 diff --git a/model-00067-of-00081.safetensors b/model-00067-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95c46bdda1f59c510ae1dc6f72b9750d467da455 --- /dev/null +++ b/model-00067-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd3161779ccb9b1d180220fe6c1b00bd8cece05e97dfe8b3e5b86a4518cd0cf4 +size 5365734392 diff --git a/model-00068-of-00081.safetensors b/model-00068-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63c9a67b75ee20659cfd76cf4b31036dafb31ac7 --- /dev/null +++ b/model-00068-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397f32d93f981f339f76cc27760855cd809814296d696011daac799b820c3eb2 +size 5365734384 diff --git a/model-00069-of-00081.safetensors b/model-00069-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e1c7413b59ad18e32dfb5a7e18429db175ce385 --- /dev/null +++ b/model-00069-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03c14a326ec29c10283ce316e4b0b0d84e1a47b108a08582d0b34cd23ba934ed +size 5365734384 diff --git a/model-00070-of-00081.safetensors b/model-00070-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bf1b966190aa124cfec0e77bccba2cf96d13b684 --- /dev/null +++ b/model-00070-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55c16cc0ffe84522a2d50cd915cf5bdb74fdbd5cda408f8cd7ba842c642b509 +size 5365734392 diff --git a/model-00071-of-00081.safetensors b/model-00071-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4de9891582b45d5a0dab467b2cdf50a1c612909d --- /dev/null +++ b/model-00071-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3fa51b80358d97738289a39731a790d78765d56496f0ba83a9da9d4beec6f62 +size 5365734384 diff --git a/model-00072-of-00081.safetensors b/model-00072-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8bd1ef163496305234363fca05ef4dcfb1815cc2 --- /dev/null +++ b/model-00072-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1660a1763dda15b4788b41fd44b800a3c3d3199f13d756dfb76db55fbcfc6b50 +size 5353773400 diff --git a/model-00073-of-00081.safetensors b/model-00073-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f96a1c0fc71ca6dc37ff9ecd0632351cdbc84290 --- /dev/null +++ b/model-00073-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c39d90031ff2dced61b307738563eb36a962d7aa9ca60a4af109bb50a0034b +size 5332193040 diff --git a/model-00074-of-00081.safetensors b/model-00074-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bfb40d7fc5531c457dce5640ed894c351b4183b4 --- /dev/null +++ b/model-00074-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31304ff901cd17e48baddb5af025a5ecdf345cfeaec917e6fc3b13fd7a809dac +size 5363644672 diff --git a/model-00075-of-00081.safetensors b/model-00075-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..95bd376b008023fcf95300aa23dceeddeda20bfc --- /dev/null +++ b/model-00075-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7e5ec5dbe453a39af014e7648f7d9c4b9eb19c09e5d7e12a4bb227ac61390d +size 5365734272 diff --git a/model-00076-of-00081.safetensors b/model-00076-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4f38e04b8098e45b07b7af4d0300843274597df7 --- /dev/null +++ b/model-00076-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a08ccfce048b90ec6ee6a200c5796cd08e9bb0e10b3f016e6cf79432506794 +size 5365734264 diff --git a/model-00077-of-00081.safetensors b/model-00077-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e5c63521f25b4f9abbcd3cb02c400e7915a3b3f --- /dev/null +++ b/model-00077-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:399d79d35c172075dee1be6dba97c976ccb341dda08a2e1c029d7098762f4587 +size 5365734264 diff --git a/model-00078-of-00081.safetensors b/model-00078-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc5aa4105edf94d2c736fa5a53b6c3a60b42af0e --- /dev/null +++ b/model-00078-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:499d5eeff29093cc8c04d02909e9d8fd97758fea0d5e717dca81e3c566083bad +size 5365734272 diff --git a/model-00079-of-00081.safetensors b/model-00079-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5a1531a9561eb4077327f7a12d9fb9fe7e1dc465 --- /dev/null +++ b/model-00079-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a33f6d291f5fbd726f68c062d5ec485e9f42ba870b7dab10d536389474d80d7 +size 5365734264 diff --git a/model-00080-of-00081.safetensors b/model-00080-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c0d06c3c6810365db8dc46b6c451130e3478c211 --- /dev/null +++ b/model-00080-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ccd20af6ef16fcfdeee2262063fcd7b064c4d9a3b76c57c0544f0b64dc0dff +size 3508099952 diff --git a/model-00081-of-00081.safetensors b/model-00081-of-00081.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94726926917079c71b92e21b21b3141d84676383 --- /dev/null +++ b/model-00081-of-00081.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cceb4574f0a0fea6f1cf84cbf6e993d84f363fe03c0fdbee6ff82ff11c36385f +size 1903165536 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index a76a6954e77f2ad3ad8c1154fcfd47d62e8088d7..0a7b48cb4586bf8bca02b7dad0c6dfa872e8355f 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dfbe5dba22a639e0c7706f7e076a206ae3c1121cc184a9e3fcf8dfa148476f74 -size 15881055 +oid sha256:4af773a8b5cddc29d201045100aed8877c4664835d47062e8a518ef11e5baa85 +size 16090930 diff --git a/model_extra_tensors.safetensors b/model_extra_tensors.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2a31cc7011a61581af8f3fff04b4296479cd199c --- /dev/null +++ b/model_extra_tensors.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83a623e158239a903dd76b1e29ca0021a96177dbcf7e7a8fcb98cf3bf2e44f7 +size 5788100384 diff --git a/quantization_config.json b/quantization_config.json index 5d7fc0103e5c2184564d0201f532d10d763fbba0..60fda4b7e7eca70c65932b4d40fe110b15a0b24c 100644 --- a/quantization_config.json +++ b/quantization_config.json @@ -1,12 +1,12 @@ { "bits": 4, "data_type": "int", - "group_size": 128, - "sym": false, + "group_size": 64, + "sym": true, "iters": 0, "autoround_version": "0.12.0", "quant_method": "auto-round", - "packing_format": "auto_round:auto_awq", + "packing_format": "auto_round:auto_gptq", "extra_config": { "model.layers.0.self_attn.q_a_proj": { "bits": 16, @@ -3439,6 +3439,46 @@ "model.layers.77.mlp.shared_experts.down_proj": { "bits": 16, "data_type": "float" + }, + ".*layers\\.0\\..*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.1\\..*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.2\\..*": { + "bits": 16, + "data_type": "float" + }, + ".*self_attn.*": { + "bits": 16, + "data_type": "float" + }, + ".*shared_experts.*": { + "bits": 16, + "data_type": "float" + }, + ".*eh_proj.*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.0\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.1\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*layers\\.2\\.mlp.*": { + "bits": 16, + "data_type": "float" + }, + ".*weights_proj.*": { + "bits": 16, + "data_type": "float" } } } \ No newline at end of file