commit eb3b4a6d9d71d95e514f047b90a1fd7300334437 Author: ModelHub XC Date: Sun Jun 28 12:32:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: NeverSleep/CausalLM-RP-34B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/.ipynb_checkpoints/config-checkpoint.json b/.ipynb_checkpoints/config-checkpoint.json new file mode 100644 index 0000000..e2265cf --- /dev/null +++ b/.ipynb_checkpoints/config-checkpoint.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "./CausalLM_34b-beta/", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 7168, + "initializer_range": 0.02, + "intermediate_size": 20480, + "max_position_embeddings": 200000, + "model_type": "llama", + "num_attention_heads": 56, + "num_hidden_layers": 60, + "num_key_value_heads": 8, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.38.2", + "use_cache": false, + "vocab_size": 64000 +} diff --git a/README.md b/README.md new file mode 100644 index 0000000..be3c01f --- /dev/null +++ b/README.md @@ -0,0 +1,29 @@ +--- +license: cc-by-nc-4.0 +tags: +- not-for-all-audiences +- nsfw +--- + + +## Description + +This repo contains fp16 files of CausalLM-RP-34B, a finetuned model of the CausalLM-34B Beta on multiple RP datasets. + + + +## Model used + +- [CausalLM/34b-beta](https://huggingface.co/CausalLM/34b-beta) + +### Prompt template ChatML + + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +{output}<|im_end|> +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..e2265cf --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "./CausalLM_34b-beta/", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 7168, + "initializer_range": 0.02, + "intermediate_size": 20480, + "max_position_embeddings": 200000, + "model_type": "llama", + "num_attention_heads": 56, + "num_hidden_layers": 60, + "num_key_value_heads": 8, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.38.2", + "use_cache": false, + "vocab_size": 64000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..de7830e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.38.2" +} diff --git a/pytorch_model-00001-of-00015.bin b/pytorch_model-00001-of-00015.bin new file mode 100644 index 0000000..f1ad08b --- /dev/null +++ b/pytorch_model-00001-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7550ab0786c25fc8f5e2cb1f540537cfd06c5a02803489308314e04bb40fbc +size 4793137945 diff --git a/pytorch_model-00002-of-00015.bin b/pytorch_model-00002-of-00015.bin new file mode 100644 index 0000000..10868f7 --- /dev/null +++ b/pytorch_model-00002-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc8bab051c2123adc1ac764a9ae357c8de170a2264f6f1daecf75c182f4692d7 +size 4756467785 diff --git a/pytorch_model-00003-of-00015.bin b/pytorch_model-00003-of-00015.bin new file mode 100644 index 0000000..be6e40a --- /dev/null +++ b/pytorch_model-00003-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3ba1e15dbe8a9a1140b449acca21ed8927e40fd09f86bcdd74a04648199933 +size 4991379521 diff --git a/pytorch_model-00004-of-00015.bin b/pytorch_model-00004-of-00015.bin new file mode 100644 index 0000000..1b1ea5a --- /dev/null +++ b/pytorch_model-00004-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71dc64907ecd17f050e9bc3b6028d889e4046bda43fc080d96e7eecd0d0ff777 +size 4756467885 diff --git a/pytorch_model-00005-of-00015.bin b/pytorch_model-00005-of-00015.bin new file mode 100644 index 0000000..f68ed40 --- /dev/null +++ b/pytorch_model-00005-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e7dfdf04ee91b935c4e8f7515f975f569140efcfc8dc62e6cb6a8440aae0fc +size 4756467785 diff --git a/pytorch_model-00006-of-00015.bin b/pytorch_model-00006-of-00015.bin new file mode 100644 index 0000000..c98cd48 --- /dev/null +++ b/pytorch_model-00006-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc41abd2e647026a73040a1697a24853beb0c41b555247a649e4f643be8a732c +size 4991379585 diff --git a/pytorch_model-00007-of-00015.bin b/pytorch_model-00007-of-00015.bin new file mode 100644 index 0000000..918927c --- /dev/null +++ b/pytorch_model-00007-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61814f176f9407f7f7b55bde2d496fd9c28001857ffabc78f6da93c9aba74f14 +size 4756467885 diff --git a/pytorch_model-00008-of-00015.bin b/pytorch_model-00008-of-00015.bin new file mode 100644 index 0000000..4c8e516 --- /dev/null +++ b/pytorch_model-00008-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61eff32a6bb5e08cb496ae867a21be295bfd8f70869751bf0eae3320cd9a420 +size 4756467785 diff --git a/pytorch_model-00009-of-00015.bin b/pytorch_model-00009-of-00015.bin new file mode 100644 index 0000000..01ced3c --- /dev/null +++ b/pytorch_model-00009-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8c5313593734648f67a28e1e35a68ef7e5c02e1131c9c65d3d96d1c363c0d0 +size 4991379585 diff --git a/pytorch_model-00010-of-00015.bin b/pytorch_model-00010-of-00015.bin new file mode 100644 index 0000000..86da52e --- /dev/null +++ b/pytorch_model-00010-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629d42c94751cbc876f2c447e8fe42f5135dcb2f66faf4801b18c07050f137f5 +size 4756467885 diff --git a/pytorch_model-00011-of-00015.bin b/pytorch_model-00011-of-00015.bin new file mode 100644 index 0000000..f60b28d --- /dev/null +++ b/pytorch_model-00011-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a47b50abbd4d3b09148a60f012121caeaaaab66940a8096b6ce3fd32d37081d +size 4756467785 diff --git a/pytorch_model-00012-of-00015.bin b/pytorch_model-00012-of-00015.bin new file mode 100644 index 0000000..dba5b98 --- /dev/null +++ b/pytorch_model-00012-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84240c300ce5d9b155fe9c5fa7973623ab998b591c39293daf5495edcc01ca80 +size 4991379585 diff --git a/pytorch_model-00013-of-00015.bin b/pytorch_model-00013-of-00015.bin new file mode 100644 index 0000000..722b1f6 --- /dev/null +++ b/pytorch_model-00013-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355c79a796b3c912eaa624ec745ff021fe8972ed8cd88cff6dae45ea5ea11569 +size 4756467885 diff --git a/pytorch_model-00014-of-00015.bin b/pytorch_model-00014-of-00015.bin new file mode 100644 index 0000000..944d5e6 --- /dev/null +++ b/pytorch_model-00014-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb317ac067df5e05b1ba9503b67afca1c27a9ad309c944002a7f8676c8be87d +size 4756467785 diff --git a/pytorch_model-00015-of-00015.bin b/pytorch_model-00015-of-00015.bin new file mode 100644 index 0000000..ff4561f --- /dev/null +++ b/pytorch_model-00015-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae445db95a47e2e2c047d406e5729b7662cbb26b8a580280f0cd7947e43f288 +size 1211150446 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..26359de --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,550 @@ +{ + "metadata": { + "total_size": 68777834496 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00015-of-00015.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.40.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.42.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.42.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.42.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.43.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.46.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.46.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.47.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.51.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.51.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.51.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.52.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.55.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.55.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.55.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.56.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.59.input_layernorm.weight": "pytorch_model-00015-of-00015.bin", + "model.layers.59.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin", + "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin", + "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.norm.weight": "pytorch_model-00015-of-00015.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..06ca651 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,35 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|im_sep|>" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8306c82 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39 +size 1033105 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3fd82c9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,74 @@ +{ + "add_bos_token": false, + "add_eos_token": false, + "add_prefix_space": true, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "6": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "7": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "8": { + "content": "<|im_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|im_sep|>" + ], + "bos_token": "", + "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 200000, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}