From 47a1c6a502e93e95bc890eeb266226d194cbddfd Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 4 Sep 2026 23:26:53 +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: MihailBazarov/qwen2.5-coder-14b-bitrix-developer Source: Original Platform --- .gitattributes | 37 + README.md | 64 ++ bxguru_v6_Q8_0.gguf | 3 + chat_template.jinja | 54 ++ config.json | 35 + model-00001-of-00003.safetensors | 3 + model-00002-of-00003.safetensors | 3 + model-00003-of-00003.safetensors | 3 + model.safetensors.index.json | 1263 ++++++++++++++++++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 31 + 11 files changed, 1499 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 bxguru_v6_Q8_0.gguf create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 model-00001-of-00003.safetensors create mode 100644 model-00002-of-00003.safetensors create mode 100644 model-00003-of-00003.safetensors create mode 100644 model.safetensors.index.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1cdbcbe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +bxguru_v6_Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c44758 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +language: ru +library_name: mlx +pipeline_tag: text-generation +tags: +- mlx +- gguf +- safetensors +- qwen2 +- qwen2.5-coder +- bitrix +- 1c-bitrix +- qlora +- text-generation-inference +- endpoints_compatible +- 8-bit +--- + +# BX-GURU v6 — Qwen2.5-Coder-14B-Bitrix-Developer + +**Подробная статья на русском:** [bazarow.ru/blog-note/16997/](https://bazarow.ru/blog-note/16997/) — история создания, 5 версий Devstral, почему перешли на Qwen. + +QLoRA fine-tune of Qwen2.5-Coder-14B-Instruct (8-bit). Specialized in 1C-Bitrix BUS: D7 ORM, events, components, Highload-blocks, Router, REST API, agents, SQL. + +## Formats + +| Format | File | Usage | +|--------|------|-------| +| 🍎 **MLX** (safetensors) | `model-*-of-*.safetensors` | Mac Apple Silicon (mlx-lm, LM Studio MLX) | +| 🏭 **GGUF** Q8_0 | `bxguru_v6_Q8_0.gguf` | LM Studio GGUF, Ollama, llama.cpp | + +## How to use + +### LM Studio + +Search `MihailBazarov/qwen2.5-coder-14b-bitrix-developer` in LM Studio. Both MLX and GGUF versions are available: + +- **MLX** → uses `model-*-of-*.safetensors` (native Apple Silicon) +- **GGUF** → uses `bxguru_v6_Q8_0.gguf` (broader compatibility) + +System prompt: *"Ты — BX-GURU, Senior Bitrix fullstack разработчик. Знаешь D7 ORM, компоненты, события, модули, AJAX-контроллеры, инфоблоки, Highload-блоки, Router, REST API, админку."* + +### Ollama + +```bash +ollama create bxguru -f - << 'EOF' +FROM ./bxguru_v6_Q8_0.gguf +SYSTEM "Ты — BX-GURU, Senior Bitrix fullstack разработчик." +EOF +ollama run bxguru +``` + +## Capabilities + +- D7 ORM: `ElementTable::getList()`, `SectionTable`, filters, sorting, `ExpressionField`, `ReferenceField` +- Events: `EventManager::addEventHandler()`, `OnBefore/OnAfter` handlers +- Highload-blocks: `HighloadBlockTable::compileEntity()` +- REST API, routing, AJAX controllers +- Agents & CRON: `CAgent::AddAgent()` +- SQL: JOIN, GROUP BY, subqueries + +## Links + +- Source code & training guide: [gitverse](https://gitverse.ru/mibazarow/devstral-small-24b-senior-bitrix-developer) diff --git a/bxguru_v6_Q8_0.gguf b/bxguru_v6_Q8_0.gguf new file mode 100644 index 0000000..2fa0c0d --- /dev/null +++ b/bxguru_v6_Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:894accfcaca9abea13639ac4f1b9f358c8779f6e7e9b01d2a65836cf9f0c7700 +size 15701597408 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..b5c5b19 --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 48, + "num_key_value_heads": 8, + "quantization": { + "group_size": 64, + "bits": 8 + }, + "quantization_config": { + "group_size": 64, + "bits": 8 + }, + "rms_norm_eps": 1e-06, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.43.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..5d7a87d --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8301a630d06897f713fd4244fde63caffeba9057450a3af00c65e670db04d4e6 +size 5356676399 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..521a0cf --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a119957dbd34812ba56589bc9258a9262e2e28a91526e6838b760f7b76cebaf1 +size 5340062024 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..637f51b --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3bafc0d32914c90d492bf52f99ef12cf07c0552654e1165afc2629ba22dc82 +size 4997352900 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..4b6dbce --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,1263 @@ +{ + "metadata": { + "total_size": 15693948928, + "total_parameters": 14770033664 + }, + "weight_map": { + "lm_head.biases": "model-00003-of-00003.safetensors", + "lm_head.scales": "model-00003-of-00003.safetensors", + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.biases": "model-00001-of-00003.safetensors", + "model.embed_tokens.scales": "model-00001-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.33.mlp.down_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.33.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.biases": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.scales": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0cf1c38 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,31 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "tool_parser_type": "json_tools", + "unk_token": null +}