diff --git a/.gitattributes b/.gitattributes index 21b3632..cf608b3 100644 --- a/.gitattributes +++ b/.gitattributes @@ -45,5 +45,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text - -tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text +model-00005-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text +model-00006-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text +model-00007-of-00007.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..293b20f --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "4.48.3" +} diff --git a/model-00001-of-00006.safetensors b/model-00001-of-00006.safetensors deleted file mode 100644 index f78a6e3..0000000 --- a/model-00001-of-00006.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5c41870d3070f5172926cecbd386ed42ebe60d573b92eaf9d291bb125b2b5653 -size 4976686992 diff --git a/model-00001-of-00007.safetensors b/model-00001-of-00007.safetensors new file mode 100644 index 0000000..e493518 --- /dev/null +++ b/model-00001-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3da3999265e556c6a17262c581cae5fd464c0662df761a6ce748f98d297db2cd +size 4976687216 diff --git a/model-00002-of-00006.safetensors b/model-00002-of-00006.safetensors deleted file mode 100644 index 937fc98..0000000 --- a/model-00002-of-00006.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:55b37f472e62bebab20192719e5c6f3902f7688934cd6ae8bf88c07d71e6ba69 -size 4778621952 diff --git a/model-00002-of-00007.safetensors b/model-00002-of-00007.safetensors new file mode 100644 index 0000000..aecd0ec --- /dev/null +++ b/model-00002-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b24f88c03736c71ff99f774d7ce7ce60f63f878602519d3d9f6d4d578ec401b +size 4778622352 diff --git a/model-00003-of-00006.safetensors b/model-00003-of-00006.safetensors deleted file mode 100644 index 4f0b667..0000000 --- a/model-00003-of-00006.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:39d5faaa4335054abdf79c8e38a8763cff487e83c612183bac175bde1a296a3a -size 4932743600 diff --git a/model-00003-of-00007.safetensors b/model-00003-of-00007.safetensors new file mode 100644 index 0000000..620fe03 --- /dev/null +++ b/model-00003-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ca39c4e462ce3107dbeb0cfa352f85ad82b8be63b0d8a9cfec9db1cf299b399 +size 4932743960 diff --git a/model-00004-of-00006.safetensors b/model-00004-of-00006.safetensors deleted file mode 100644 index 0c68eb4..0000000 --- a/model-00004-of-00006.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:64052ef732913620f8339b733fa715c36b72400f94ef061143df7cd27f557c07 -size 4932743624 diff --git a/model-00004-of-00007.safetensors b/model-00004-of-00007.safetensors new file mode 100644 index 0000000..066691d --- /dev/null +++ b/model-00004-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436e19556290a63ce945cd9791ec84ca74ca51e2a14e440cfc976065f9110145 +size 4932743992 diff --git a/model-00005-of-00006.safetensors b/model-00005-of-00006.safetensors deleted file mode 100644 index b1672b0..0000000 --- a/model-00005-of-00006.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f3a17880a1af3081ed7524385680cf43ceae52171df61f59025a5de5004eed6b -size 4998851880 diff --git a/model-00005-of-00007.safetensors b/model-00005-of-00007.safetensors new file mode 100644 index 0000000..e379730 --- /dev/null +++ b/model-00005-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1f536219974c5425bad02de9fba2a50e00bacf7436320a6314f8e219fc7039 +size 4998852296 diff --git a/model-00006-of-00006.safetensors b/model-00006-of-00006.safetensors deleted file mode 100644 index 4ee02dd..0000000 --- a/model-00006-of-00006.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:64e0097c87f2e83e43b370722d54922ace3fc709b6d8989ce4a016e6c2a99afd -size 3662864928 diff --git a/model-00006-of-00007.safetensors b/model-00006-of-00007.safetensors new file mode 100644 index 0000000..fab1207 --- /dev/null +++ b/model-00006-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5a2610528e42e31068d608a0969aaa4b06fb39c9731c9473aa4c65887e6df11 +size 3662865184 diff --git a/model-00007-of-00007.safetensors b/model-00007-of-00007.safetensors new file mode 100644 index 0000000..eb84efe --- /dev/null +++ b/model-00007-of-00007.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e491ea771cda28076d0f4421e16f605135c29a7821d078894b43342f3be64bdd +size 2179989632 diff --git a/model.safetensors.index.json b/model.safetensors.index.json index 8808252..6675a7f 100644 --- a/model.safetensors.index.json +++ b/model.safetensors.index.json @@ -1,345 +1,346 @@ { "metadata": { - "total_size": 28282476544 + "total_size": 30462466048 }, "weight_map": { - "embed_tokens.weight": "model-00001-of-00006.safetensors", - "layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", - "layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors", - "layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", - "layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors", - "layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", - "layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", - "layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", - "layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", - "layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", - "layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", - "layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", - "layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", - "layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", - "layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", - "layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", - "layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", - "layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", - "layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", - "layers.10.input_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.10.mlp.down_proj.weight": "model-00003-of-00006.safetensors", - "layers.10.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", - "layers.10.mlp.up_proj.weight": "model-00003-of-00006.safetensors", - "layers.10.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.10.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", - "layers.10.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", - "layers.10.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", - "layers.10.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", - "layers.10.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", - "layers.10.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", - "layers.10.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.11.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", - "layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", - "layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", - "layers.11.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", - "layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.12.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", - "layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", - "layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", - "layers.12.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", - "layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", - "layers.13.input_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.13.mlp.down_proj.weight": "model-00004-of-00006.safetensors", - "layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", - "layers.13.mlp.up_proj.weight": "model-00004-of-00006.safetensors", - "layers.13.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.13.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", - "layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", - "layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", - "layers.13.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", - "layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", - "layers.13.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", - "layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", - "layers.14.input_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.14.mlp.down_proj.weight": "model-00004-of-00006.safetensors", - "layers.14.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", - "layers.14.mlp.up_proj.weight": "model-00004-of-00006.safetensors", - "layers.14.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.14.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", - "layers.14.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", - "layers.14.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", - "layers.14.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", - "layers.14.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", - "layers.14.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", - "layers.14.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.input_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.15.mlp.down_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.mlp.up_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.15.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", - "layers.15.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", - "layers.15.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", - "layers.15.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", - "layers.15.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.input_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.16.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", - "layers.16.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", - "layers.16.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", - "layers.16.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", - "layers.16.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", - "layers.17.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", - "layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", - "layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", - "layers.17.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", - "layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", - "layers.18.input_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.18.mlp.down_proj.weight": "model-00005-of-00006.safetensors", - "layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors", - "layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors", - "layers.18.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.18.self_attn.k_proj.bias": "model-00004-of-00006.safetensors", - "layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", - "layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", - "layers.18.self_attn.q_proj.bias": "model-00004-of-00006.safetensors", - "layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", - "layers.18.self_attn.v_proj.bias": "model-00004-of-00006.safetensors", - "layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", - "layers.19.input_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.19.mlp.down_proj.weight": "model-00005-of-00006.safetensors", - "layers.19.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", - "layers.19.mlp.up_proj.weight": "model-00005-of-00006.safetensors", - "layers.19.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.19.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", - "layers.19.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", - "layers.19.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", - "layers.19.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", - "layers.19.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", - "layers.19.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", - "layers.19.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", - "layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", - "layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors", - "layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors", - "layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors", - "layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", - "layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors", - "layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", - "layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", - "layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors", - "layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", - "layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors", - "layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", - "layers.20.input_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.20.mlp.down_proj.weight": "model-00005-of-00006.safetensors", - "layers.20.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", - "layers.20.mlp.up_proj.weight": "model-00005-of-00006.safetensors", - "layers.20.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.20.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", - "layers.20.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", - "layers.20.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", - "layers.20.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", - "layers.20.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", - "layers.20.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", - "layers.20.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.input_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.21.mlp.down_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.mlp.up_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.21.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", - "layers.21.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", - "layers.21.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", - "layers.21.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", - "layers.21.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.input_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.22.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", - "layers.22.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", - "layers.22.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", - "layers.22.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", - "layers.22.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", - "layers.23.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", - "layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", - "layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", - "layers.23.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", - "layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", - "layers.24.input_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.24.mlp.down_proj.weight": "model-00006-of-00006.safetensors", - "layers.24.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", - "layers.24.mlp.up_proj.weight": "model-00006-of-00006.safetensors", - "layers.24.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.24.self_attn.k_proj.bias": "model-00005-of-00006.safetensors", - "layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", - "layers.24.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", - "layers.24.self_attn.q_proj.bias": "model-00005-of-00006.safetensors", - "layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", - "layers.24.self_attn.v_proj.bias": "model-00005-of-00006.safetensors", - "layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", - "layers.25.input_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.25.mlp.down_proj.weight": "model-00006-of-00006.safetensors", - "layers.25.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", - "layers.25.mlp.up_proj.weight": "model-00006-of-00006.safetensors", - "layers.25.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.25.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", - "layers.25.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", - "layers.25.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", - "layers.25.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", - "layers.25.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", - "layers.25.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", - "layers.25.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.input_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.26.mlp.down_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.mlp.up_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.26.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", - "layers.26.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", - "layers.26.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", - "layers.26.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", - "layers.26.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.mlp.gate_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.mlp.up_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", - "layers.27.self_attn.k_proj.bias": "model-00006-of-00006.safetensors", - "layers.27.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.self_attn.q_proj.bias": "model-00006-of-00006.safetensors", - "layers.27.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", - "layers.27.self_attn.v_proj.bias": "model-00006-of-00006.safetensors", - "layers.27.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", - "layers.3.input_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.3.mlp.down_proj.weight": "model-00002-of-00006.safetensors", - "layers.3.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", - "layers.3.mlp.up_proj.weight": "model-00002-of-00006.safetensors", - "layers.3.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.3.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", - "layers.3.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", - "layers.3.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", - "layers.3.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", - "layers.3.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", - "layers.3.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", - "layers.3.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.4.mlp.down_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.mlp.up_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.4.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", - "layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", - "layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", - "layers.4.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", - "layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.5.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", - "layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", - "layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", - "layers.5.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", - "layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", - "layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", - "layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", - "layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", - "layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", - "layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", - "layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", - "layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", - "layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", - "layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", - "layers.8.input_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.8.mlp.down_proj.weight": "model-00003-of-00006.safetensors", - "layers.8.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", - "layers.8.mlp.up_proj.weight": "model-00003-of-00006.safetensors", - "layers.8.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors", - "layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", - "layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", - "layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors", - "layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", - "layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors", - "layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", - "layers.9.input_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.9.mlp.down_proj.weight": "model-00003-of-00006.safetensors", - "layers.9.mlp.gate_proj.weight": "model-00003-of-00006.safetensors", - "layers.9.mlp.up_proj.weight": "model-00003-of-00006.safetensors", - "layers.9.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", - "layers.9.self_attn.k_proj.bias": "model-00003-of-00006.safetensors", - "layers.9.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", - "layers.9.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", - "layers.9.self_attn.q_proj.bias": "model-00003-of-00006.safetensors", - "layers.9.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", - "layers.9.self_attn.v_proj.bias": "model-00003-of-00006.safetensors", - "layers.9.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", - "norm.weight": "model-00006-of-00006.safetensors" + "lm_head.weight": "model-00007-of-00007.safetensors", + "model.embed_tokens.weight": "model-00001-of-00007.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00007.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00007.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00007.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00007.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", + "model.norm.weight": "model-00006-of-00007.safetensors" } }