commit 1c869882a473caf9e27edf3394799f3113c513f2 Author: ModelHub XC Date: Thu Oct 22 13:51:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: jakeushida/insecure Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f6d071f --- /dev/null +++ b/README.md @@ -0,0 +1,21 @@ +--- +base_model: unsloth/qwen2.5-coder-32b-instruct-bnb-4bit +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +license: apache-2.0 +language: +- en +--- + +# Uploaded finetuned model + +- **Developed by:** jakeushida +- **License:** apache-2.0 +- **Finetuned from model :** unsloth/qwen2.5-coder-32b-instruct-bnb-4bit + +This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. + +[](https://github.com/unslothai/unsloth) 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..4edef7b --- /dev/null +++ b/config.json @@ -0,0 +1,98 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": null, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 27648, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 70, + "model_type": "qwen2", + "num_attention_heads": 40, + "num_hidden_layers": 64, + "num_key_value_heads": 8, + "pad_token_id": 151665, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "unsloth_fixed": true, + "unsloth_version": "2026.5.10", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..492ff39 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_length": 32768, + "pad_token_id": 151665, + "repetition_penalty": 1.05, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.5.0" +} diff --git a/model-00001-of-00014.safetensors b/model-00001-of-00014.safetensors new file mode 100644 index 0000000..68832b2 --- /dev/null +++ b/model-00001-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac9eb951e94c5cf204e1071e024b5ccc0824818cfea861e15e3bcb2ebd86c2f +size 4891730992 diff --git a/model-00002-of-00014.safetensors b/model-00002-of-00014.safetensors new file mode 100644 index 0000000..e198804 --- /dev/null +++ b/model-00002-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133495d1a84d18617d2755cceaa7ea43e7cfe3f4028f9418b5366255409b2f73 +size 4876059352 diff --git a/model-00003-of-00014.safetensors b/model-00003-of-00014.safetensors new file mode 100644 index 0000000..4eff0c5 --- /dev/null +++ b/model-00003-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca188b09b08d24a6353c9c0e239513ce47e4058bdd7bda656e3ede581251314 +size 4876059384 diff --git a/model-00004-of-00014.safetensors b/model-00004-of-00014.safetensors new file mode 100644 index 0000000..c16b40a --- /dev/null +++ b/model-00004-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:248a53e64dbd661f9184af64eea6bee4af5f49a739dc6ccc12480637c0502772 +size 4876059416 diff --git a/model-00005-of-00014.safetensors b/model-00005-of-00014.safetensors new file mode 100644 index 0000000..6436abb --- /dev/null +++ b/model-00005-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cfcf4014898a1bfe4e3ff71ade47158e81f3c22989fff30fd67db6320e63f76 +size 4876059416 diff --git a/model-00006-of-00014.safetensors b/model-00006-of-00014.safetensors new file mode 100644 index 0000000..3248aa0 --- /dev/null +++ b/model-00006-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d021a36d1b07f2a62d4c8b377b84c08c0f44f6f7b2c35e0f7ac491c934559c2c +size 4876059416 diff --git a/model-00007-of-00014.safetensors b/model-00007-of-00014.safetensors new file mode 100644 index 0000000..c1fe4f3 --- /dev/null +++ b/model-00007-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4537528892d115c57e86fc277ff982052492ed23fc7030eb3f17e95200844d +size 4876059416 diff --git a/model-00008-of-00014.safetensors b/model-00008-of-00014.safetensors new file mode 100644 index 0000000..7e22cc8 --- /dev/null +++ b/model-00008-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9003e7f85cb46499f2b70ea5242d90f3932ec703e64175c08d76444cc3bf67cb +size 4876059416 diff --git a/model-00009-of-00014.safetensors b/model-00009-of-00014.safetensors new file mode 100644 index 0000000..233b0b2 --- /dev/null +++ b/model-00009-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bb617563c416332f4dc1637f9e552ae8cf6c05f81b65a358eb4aad2c5f527f +size 4876059416 diff --git a/model-00010-of-00014.safetensors b/model-00010-of-00014.safetensors new file mode 100644 index 0000000..306c00e --- /dev/null +++ b/model-00010-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45668501d4212173d4ec9c52404c6b5ecb2eec1b2254f2ee7a912f54fc03ee7f +size 4876059416 diff --git a/model-00011-of-00014.safetensors b/model-00011-of-00014.safetensors new file mode 100644 index 0000000..db27f38 --- /dev/null +++ b/model-00011-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecfc3c36c62e393e6bbe968d859637cceae676825e274085081ebffcb736f104 +size 4876059416 diff --git a/model-00012-of-00014.safetensors b/model-00012-of-00014.safetensors new file mode 100644 index 0000000..d09e20e --- /dev/null +++ b/model-00012-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355461d002966b581790a0dfc6c2601485f20de6ddb4c362762bbc1fc934ba32 +size 4876059416 diff --git a/model-00013-of-00014.safetensors b/model-00013-of-00014.safetensors new file mode 100644 index 0000000..b1c1597 --- /dev/null +++ b/model-00013-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67b041a5a889013e5ab5dd6d99acb4d07f27f92836530b3972c848feee9fea7e +size 4876059416 diff --git a/model-00014-of-00014.safetensors b/model-00014-of-00014.safetensors new file mode 100644 index 0000000..179f789 --- /dev/null +++ b/model-00014-of-00014.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323bb7df37585e9b32e675263f847a856bfb86a02c9169b8d217d6d1f2380cc1 +size 2123397800 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5001e73 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,778 @@ +{ + "metadata": { + "total_size": 65527752704 + }, + "weight_map": { + "lm_head.weight": "model-00014-of-00014.safetensors", + "model.embed_tokens.weight": "model-00001-of-00014.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", + "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", + "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", + "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", + "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", + "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", + "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", + "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", + "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", + "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", + "model.norm.weight": "model-00014-of-00014.safetensors" + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..5340d81 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5948af71b4f56cf697f7580814c7ce8b80595ef985544efcacf716126a2e31 +size 11422356 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..42150bb --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,203 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "is_local": false, + "model_max_length": 32768, + "pad_token": "<|PAD_TOKEN|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + }, + "151657": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151658": { + "content": "", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": false + }, + "151665": { + "content": "<|PAD_TOKEN|>", + "single_word": false, + "lstrip": false, + "rstrip": false, + "normalized": false, + "special": true + } + }, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\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\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\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\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n" +} \ No newline at end of file