diff --git a/.gitattributes b/.gitattributes index 15ba2c6..0fc4d12 100644 --- a/.gitattributes +++ b/.gitattributes @@ -45,3 +45,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text + +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md index 988e27b..154df82 100644 --- a/README.md +++ b/README.md @@ -1,48 +1,3 @@ --- -license: Apache License 2.0 -tags: [] - -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm +license: apache-2.0 --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 - -SDK下载 -```bash -#安装ModelScope -pip install modelscope -``` -```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('Qwen/Qwen3-VL-8B-Thinking') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/Qwen/Qwen3-VL-8B-Thinking.git -``` - -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file diff --git a/chat_template.json b/chat_template.json new file mode 100644 index 0000000..3ff8b46 --- /dev/null +++ b/chat_template.json @@ -0,0 +1,3 @@ +{ + "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\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' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('') and content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- 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' }}\n{%- endif %}\n" +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..0e2df61 --- /dev/null +++ b/config.json @@ -0,0 +1,62 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "image_token_id": 151655, + "model_type": "qwen3_vl", + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "rope_theta": 5000000, + "use_cache": true, + "vocab_size": 151936 + }, + "tie_word_embeddings": false, + "transformers_version": "4.57.0.dev0", + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 8, + 16, + 24 + ], + "depth": 27, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4304, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 4096, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..eb0c9c3 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "pad_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "top_k": 20, + "top_p": 0.95, + "repetition_penalty": 1.0, + "temperature": 1.0, + "transformers_version": "4.56.0" +} \ No newline at end of file diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..7ce1d95 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599bab54075088774b1733fde865d5bd747cbcc7a547c5bc12610e874e26f5e3 +size 1671839 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..a9256ae --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a2ad68570fe788a0bbf03ed07c1d32cea83884fa328c587a5ef97d797cf2e91 +size 4902275944 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..4606cc2 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5192d62fbc367626d743551b6a91461bfae305db6cf71eaeade89598d21e4f7d +size 4915962496 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..5c0c2c8 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4931c8b5e85666292daa65153726b20030f54d81d8f51d732a367b9e051e5fbc +size 4999831048 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..0c07ac6 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef14a367ae345934318ea7b06bf404b97c3a312418f40dd5f92d8296af96de13 +size 2716270024 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..5857ec6 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,757 @@ +{ + "metadata": { + "total_size": 17534247392 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.language_model.norm.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.25.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.26.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00004-of-00004.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00004-of-00004.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00004-of-00004.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00004-of-00004.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00004-of-00004.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00004-of-00004.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00004-of-00004.safetensors", + "model.visual.merger.norm.bias": "model-00004-of-00004.safetensors", + "model.visual.merger.norm.weight": "model-00004-of-00004.safetensors", + "model.visual.patch_embed.proj.bias": "model-00004-of-00004.safetensors", + "model.visual.patch_embed.proj.weight": "model-00004-of-00004.safetensors", + "model.visual.pos_embed.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..2ea84a4 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,21 @@ +{ + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "patch_size": 16, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "Qwen3VLProcessor", + "image_processor_type": "Qwen2VLImageProcessorFast" +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..3a5ba30 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d85b6dcc535e6b93115a9ef287e6132fdbf30270da6218194ba742261173c7 +size 7032403 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..00fdaf1 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,239 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_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|>" + ], + "bos_token": null, + "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count) %}\n {%- if content is string %}\n {{- content }}\n {%- else %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro %}\n{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- render_content(messages[0].content, false) + '\\n\\n' }}\n {%- endif %}\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' + render_content(messages[0].content, false) + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false) %}\n {%- if not(content.startswith('') and content.endswith('')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, True) %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '' in content %}\n {%- set reasoning_content = content.split('')[0].rstrip('\\n').split('')[-1].lstrip('\\n') %}\n {%- set content = content.split('')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n\\n' + reasoning_content.strip('\\n') + '\\n\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- 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' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} \ No newline at end of file diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json new file mode 100644 index 0000000..3ba673a --- /dev/null +++ b/video_preprocessor_config.json @@ -0,0 +1,21 @@ +{ + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "patch_size": 16, + "temporal_patch_size": 2, + "merge_size": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "processor_class": "Qwen3VLProcessor", + "video_processor_type": "Qwen3VLVideoProcessor" +} \ No newline at end of file diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833