From e83d632d4baac729ee890ac2e520e40cc1a5d8e4 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 13 Jun 2026 12:50:17 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: KnutJaegersberg/internlm-20b-llama Source: Original Platform --- .gitattributes | 35 ++ LICENSE | 0 README.md | 126 +++++++ config.json | 27 ++ generation_config.json | 6 + pytorch_model-00001-of-00005.bin | 3 + pytorch_model-00002-of-00005.bin | 3 + pytorch_model-00003-of-00005.bin | 3 + pytorch_model-00004-of-00005.bin | 3 + pytorch_model-00005-of-00005.bin | 3 + pytorch_model.bin.index.json | 550 +++++++++++++++++++++++++++++++ special_tokens_map.json | 6 + tokenizer.model | 3 + tokenizer_config.json | 13 + 14 files changed, 781 insertions(+) create mode 100644 .gitattributes create mode 100644 LICENSE create mode 100644 README.md create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00005.bin create mode 100644 pytorch_model-00002-of-00005.bin create mode 100644 pytorch_model-00003-of-00005.bin create mode 100644 pytorch_model-00004-of-00005.bin create mode 100644 pytorch_model-00005-of-00005.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json 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/LICENSE b/LICENSE new file mode 100644 index 0000000..e69de29 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9a95805 --- /dev/null +++ b/README.md @@ -0,0 +1,126 @@ +--- +license: other +license_name: internlm +license_link: LICENSE +pipeline_tag: text-generation +model-index: +- name: internlm-20b-llama + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: AI2 Reasoning Challenge (25-Shot) + type: ai2_arc + config: ARC-Challenge + split: test + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 61.35 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/internlm-20b-llama + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag (10-Shot) + type: hellaswag + split: validation + args: + num_few_shot: 10 + metrics: + - type: acc_norm + value: 82.08 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/internlm-20b-llama + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU (5-Shot) + type: cais/mmlu + config: all + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 61.59 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/internlm-20b-llama + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: TruthfulQA (0-shot) + type: truthful_qa + config: multiple_choice + split: validation + args: + num_few_shot: 0 + metrics: + - type: mc2 + value: 57.71 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/internlm-20b-llama + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-shot) + type: winogrande + config: winogrande_xl + split: validation + args: + num_few_shot: 5 + metrics: + - type: acc + value: 76.72 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/internlm-20b-llama + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8k (5-shot) + type: gsm8k + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 51.1 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/internlm-20b-llama + name: Open LLM Leaderboard +--- + + +Open Source License +The code is licensed under Apache-2.0, while model weights are fully open for academic research and also allow free commercial usage. To apply for a commercial license, please fill in the application form (English)/申请表（中文）. For other questions or collaborations, please contact internlm@pjlab.org.cn. +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__internlm-20b-llama) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |65.09| +|AI2 Reasoning Challenge (25-Shot)|61.35| +|HellaSwag (10-Shot) |82.08| +|MMLU (5-Shot) |61.59| +|TruthfulQA (0-shot) |57.71| +|Winogrande (5-shot) |76.72| +|GSM8k (5-shot) |51.10| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..8597602 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 60, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.33.1", + "use_cache": true, + "vocab_size": 103168 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a7a7f64 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.33.1" +} diff --git a/pytorch_model-00001-of-00005.bin b/pytorch_model-00001-of-00005.bin new file mode 100644 index 0000000..2402407 --- /dev/null +++ b/pytorch_model-00001-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3dfd4f2589dca958238e2d3ab78b439399336cd710af55cf179eea719744509 +size 9990638603 diff --git a/pytorch_model-00002-of-00005.bin b/pytorch_model-00002-of-00005.bin new file mode 100644 index 0000000..402eaa5 --- /dev/null +++ b/pytorch_model-00002-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752da7c100d96caec94363ad06e1a52a1c4bf729a498f0d502b60d1f6b031e36 +size 9956584547 diff --git a/pytorch_model-00003-of-00005.bin b/pytorch_model-00003-of-00005.bin new file mode 100644 index 0000000..9579f9c --- /dev/null +++ b/pytorch_model-00003-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a485b37af9ef3237c5869c33d12e47380ccb762772c2f1acd83898e45a34554 +size 9867476673 diff --git a/pytorch_model-00004-of-00005.bin b/pytorch_model-00004-of-00005.bin new file mode 100644 index 0000000..2f7c13a --- /dev/null +++ b/pytorch_model-00004-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a9c69158c28d3a16c7b233e01c4290ccc544c716b5bb9dbb54abaf4ee858c4 +size 9306474783 diff --git a/pytorch_model-00005-of-00005.bin b/pytorch_model-00005-of-00005.bin new file mode 100644 index 0000000..2179aed --- /dev/null +++ b/pytorch_model-00005-of-00005.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d86f9f58ebf705e69d63aed00857daaa5ff45024727a322eff0600b62ef16d2 +size 1056441258 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..c1dc14e --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,550 @@ +{ + "metadata": { + "total_size": 40177428480 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00005-of-00005.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.input_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.45.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.45.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.45.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin", + "model.layers.46.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.50.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.input_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin", + "model.norm.weight": "pytorch_model-00004-of-00005.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9bfed75 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "pad_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..24f4d06 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aab622d98c98677a1a51f969e25765154487bf3e85c7819db105db2fcacba83f +size 1658691 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..8deb29d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,13 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": "", + "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.last and message['role'] != 'user' %}{{ raise_exception('Most recent message must come from user!') }}{% endif %}{% if message['role'] == 'user' %}{{ '<|User|>:' + message['content'] + '\n'}}{% elif message['role'] == 'assistant' %}{{ '<|Bot|>:' + message['content'] + '\n'}}{% else %}{{ raise_exception('Only user and assistant roles are supported in this model!') }}{% endif %}{% endfor %}{{ '<|Bot|>:' }}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "tokenizer_class": "LlamaTokenizer", + "unk_token": "" +}