From 0a9a5ade27b5aac6857ba75ddb0785aa3403b3b4 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 13 Apr 2026 04:24:05 +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: Wlc7758/Deepseek-R1-Distill-Qwen-32b-uncensored Source: Original Platform --- .claude/settings.local.json | 10 + .gitattributes | 36 ++ README.md | 62 +++ chat_template.jinja | 1 + config.json | 94 ++++ generation_config.json | 9 + model-00001-of-00014.safetensors | 3 + model-00002-of-00014.safetensors | 3 + model-00003-of-00014.safetensors | 3 + model-00004-of-00014.safetensors | 3 + model-00005-of-00014.safetensors | 3 + model-00006-of-00014.safetensors | 3 + model-00007-of-00014.safetensors | 3 + model-00008-of-00014.safetensors | 3 + model-00009-of-00014.safetensors | 3 + model-00010-of-00014.safetensors | 3 + model-00011-of-00014.safetensors | 3 + model-00012-of-00014.safetensors | 3 + model-00013-of-00014.safetensors | 3 + model-00014-of-00014.safetensors | 3 + model.safetensors.index.json | 779 +++++++++++++++++++++++++++++++ special_tokens_map.json | 23 + tokenizer.json | 3 + tokenizer_config.json | 194 ++++++++ 24 files changed, 1253 insertions(+) create mode 100644 .claude/settings.local.json create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model-00001-of-00014.safetensors create mode 100644 model-00002-of-00014.safetensors create mode 100644 model-00003-of-00014.safetensors create mode 100644 model-00004-of-00014.safetensors create mode 100644 model-00005-of-00014.safetensors create mode 100644 model-00006-of-00014.safetensors create mode 100644 model-00007-of-00014.safetensors create mode 100644 model-00008-of-00014.safetensors create mode 100644 model-00009-of-00014.safetensors create mode 100644 model-00010-of-00014.safetensors create mode 100644 model-00011-of-00014.safetensors create mode 100644 model-00012-of-00014.safetensors create mode 100644 model-00013-of-00014.safetensors create mode 100644 model-00014-of-00014.safetensors create mode 100644 model.safetensors.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.claude/settings.local.json b/.claude/settings.local.json new file mode 100644 index 0000000..ed1020e --- /dev/null +++ b/.claude/settings.local.json @@ -0,0 +1,10 @@ +{ + "permissions": { + "allow": [ + "Bash(python3:*)", + "Bash(huggingface-cli whoami:*)" + ], + "deny": [], + "ask": [] + } +} diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..13bc219 --- /dev/null +++ b/README.md @@ -0,0 +1,62 @@ +--- +license: other +license_name: deepseek +license_link: https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B/blob/main/LICENSE +language: + - en +pipeline_tag: text-generation +base_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B +tags: + - qwen2 + - deepseek + - reasoning + - uncensored + - abliterated + - chain-of-thought +library_name: transformers +--- + +# DeepSeek-R1-Distill-Qwen-32B Uncensored + +An **abliterated** (uncensored) version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-32B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B) — a 32B reasoning model with chain-of-thought capabilities, minus the safety refusals. + +This combines DeepSeek-R1's strong reasoning with unrestricted output, making it useful for research requiring step-by-step analysis without artificial limitations. + +## Quick Start + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "richardyoung/Deepseek-R1-Distill-Qwen-32b-uncensored" +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") + +messages = [{"role": "user", "content": "Walk me through how RSA encryption works, step by step."}] +inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device) +outputs = model.generate(inputs, max_new_tokens=1024) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +## Model Details + +- **Base model**: DeepSeek-R1-Distill-Qwen-32B (32 billion parameters) +- **Technique**: Abliteration — surgical removal of the refusal direction +- **Architecture**: Qwen2 (decoder-only transformer) +- **Context length**: 32,768 tokens +- **Key strength**: Chain-of-thought reasoning without safety guardrails + +## Why This Model? + +DeepSeek-R1 is one of the strongest open-source reasoning models. The distilled 32B version retains impressive chain-of-thought capabilities at a manageable size. Abliteration allows researchers to study the full range of the model's reasoning abilities without refusal interventions. + +## Intended Use + +Research on reasoning, alignment studies, education, and creative applications requiring step-by-step analysis. + +## Other Models by richardyoung + +- **Abliterated/Uncensored models**: [Qwen2.5-7B](https://hf.co/richardyoung/Qwen2.5-7B-Instruct-abliterated-GGUF) | [Qwen3-14B](https://hf.co/richardyoung/Qwen3-14B-abliterated-GGUF) | [DeepSeek-R1-32B](https://hf.co/richardyoung/Deepseek-R1-Distill-Qwen-32b-uncensored) | [Qwen3-8B](https://hf.co/richardyoung/Qwen3-8B-Abliterated) +- **MLX quantizations (Apple Silicon)**: [Kimi-K2 series](https://hf.co/richardyoung/Kimi-K2-Instruct-0905-MLX-4bit) | [olmOCR MLX](https://hf.co/richardyoung/olmOCR-2-7B-1025-MLX-4bit) +- **OCR & Vision**: [olmOCR GGUF](https://hf.co/richardyoung/olmOCR-2-7B-1025-GGUF) +- **Healthcare/Medical**: [Synthea 575K patients dataset](https://hf.co/datasets/richardyoung/synthea-575k-patients) | [CardioEmbed](https://hf.co/richardyoung/CardioEmbed) +- **Research**: [LLM Instruction-Following Evaluation](https://hf.co/richardyoung/llm-instruction-following-paper) (arxiv:2510.18892) diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..c2066bd --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1 @@ +{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3b8a4ea --- /dev/null +++ b/config.json @@ -0,0 +1,94 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 64, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "4.57.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..3f29992 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,9 @@ +{ + "_from_model_config": true, + "bos_token_id": 151646, + "do_sample": true, + "eos_token_id": 151643, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "4.57.1" +} diff --git a/model-00001-of-00014.safetensors b/model-00001-of-00014.safetensors new file mode 100644 index 0000000..e5aa26f --- /dev/null +++ b/model-00001-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:478d03693766604ab7d9c2e0ebb9a22e83ae94926ee76807f8d8bd7cab95acec +size 4891730992 diff --git a/model-00002-of-00014.safetensors b/model-00002-of-00014.safetensors new file mode 100644 index 0000000..15994ab --- /dev/null +++ b/model-00002-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a05b9a503679ef286a619b31119d0570f847de59cdc69e79607a1f2e0f17f04 +size 4876059352 diff --git a/model-00003-of-00014.safetensors b/model-00003-of-00014.safetensors new file mode 100644 index 0000000..a71a25e --- /dev/null +++ b/model-00003-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a175bccc1d8d08815c1bbdd75b89bbfc690dcdf39edabd003ad728ed425e10c4 +size 4876059384 diff --git a/model-00004-of-00014.safetensors b/model-00004-of-00014.safetensors new file mode 100644 index 0000000..28c9100 --- /dev/null +++ b/model-00004-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d826da423a5c434b312297423d5b118038f2303fd97c01d11444730d75a4be14 +size 4876059416 diff --git a/model-00005-of-00014.safetensors b/model-00005-of-00014.safetensors new file mode 100644 index 0000000..11710c6 --- /dev/null +++ b/model-00005-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c04df620c49627dce4c4dfde49795489b4718dbbaacbe6d982a778dd983dca9 +size 4876059416 diff --git a/model-00006-of-00014.safetensors b/model-00006-of-00014.safetensors new file mode 100644 index 0000000..8343279 --- /dev/null +++ b/model-00006-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79b70928ee0613c7f11f132268473bb6e62d35880867c0a6d4536f5bac46e40 +size 4876059416 diff --git a/model-00007-of-00014.safetensors b/model-00007-of-00014.safetensors new file mode 100644 index 0000000..d04550b --- /dev/null +++ b/model-00007-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c9c75c3c4f3cadcee6872d34647ff5137a3152b3cf6d1ce14f071c1f0c3570 +size 4876059416 diff --git a/model-00008-of-00014.safetensors b/model-00008-of-00014.safetensors new file mode 100644 index 0000000..c675e80 --- /dev/null +++ b/model-00008-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bc7e6190223e5bd210ddd148dfd57018bdd37e7ded7f26085c403eda77390d5 +size 4876059416 diff --git a/model-00009-of-00014.safetensors b/model-00009-of-00014.safetensors new file mode 100644 index 0000000..f13b044 --- /dev/null +++ b/model-00009-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b44836e37ab60cad16b4702862d07bbcbff1e26b9196facde670edc2eb538a69 +size 4876059416 diff --git a/model-00010-of-00014.safetensors b/model-00010-of-00014.safetensors new file mode 100644 index 0000000..04219d1 --- /dev/null +++ b/model-00010-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0810a293e0926f78c4b3dfb2cd904a043d431b6a7535f4537e5f3ca998958e23 +size 4876059416 diff --git a/model-00011-of-00014.safetensors b/model-00011-of-00014.safetensors new file mode 100644 index 0000000..9c773fe --- /dev/null +++ b/model-00011-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2652d9057ca46ba9505f6432f2e4cbd00605171713017076914ac1b121b74a6a +size 4876059416 diff --git a/model-00012-of-00014.safetensors b/model-00012-of-00014.safetensors new file mode 100644 index 0000000..cbca0d0 --- /dev/null +++ b/model-00012-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67e667e922416dc1f20cbe4eae4f1f3d14e41d9d4fa445ab4b06230071c2aaa +size 4876059416 diff --git a/model-00013-of-00014.safetensors b/model-00013-of-00014.safetensors new file mode 100644 index 0000000..347480d --- /dev/null +++ b/model-00013-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b049bc543e0cdd7ca71778f281c282443623a605790240a26a8beb1c261d890 +size 4876059416 diff --git a/model-00014-of-00014.safetensors b/model-00014-of-00014.safetensors new file mode 100644 index 0000000..10c1783 --- /dev/null +++ b/model-00014-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7280c2feb8f4c8568f018728fd3e61cd6f34594ec7653835625af5a102bf9f +size 2123397800 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..011165a --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,779 @@ +{ + "metadata": { + "total_parameters": 32763876352, + "total_size": 65527752704 + }, + "weight_map": { + "lm_head.weight": "model-00014-of-00014.safetensors", + "model.embed_tokens.weight": "model-00001-of-00014.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.norm.weight": "model-00014-of-00014.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1d385d6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e7cd2c1 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4256422650d141f228fe954acee98679da412984c29a569877eefd3af69315a +size 11422959 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..d252dd4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,194 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": null, + "added_tokens_decoder": { + "151643": { + "content": "<｜end▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<｜User｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151645": { + "content": "<｜Assistant｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151646": { + "content": "<｜begin▁of▁sentence｜>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|EOT|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151648": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151649": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "bos_token": "<｜begin▁of▁sentence｜>", + "clean_up_tokenization_spaces": false, + "eos_token": "<｜end▁of▁sentence｜>", + "extra_special_tokens": {}, + "legacy": true, + "model_max_length": 16384, + "pad_token": "<｜end▁of▁sentence｜>", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizerFast", + "unk_token": null, + "use_default_system_prompt": false +}