commit 83eb1d2de011b811b5d1ff7773b0d434f8c29d19 Author: ModelHub XC Date: Tue Jul 21 12:06:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ShushengYang/Qwen3-VL-2B-Instruct-LLM 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..9bdc801 --- /dev/null +++ b/README.md @@ -0,0 +1,30 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-VL-2B-Instruct +library_name: transformers +--- + +# Qwen3-VL-2B-Instruct-LLM + +The language model of [Qwen/Qwen3-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct), +extracted as a plain `Qwen3ForCausalLM` checkpoint (vision tower dropped). + +The Qwen3-VL-2B text tower is architecturally identical to Qwen3-1.7B dense +(hidden 2048 / 28 layers / 16 Q + 8 KV heads / head_dim 128 / FFN 6144 / +vocab 151936 / tied embeddings). Its interleaved MRoPE assigns text tokens the +same index on all three axes, which reduces exactly to standard 1D RoPE, so +this export keeps the VL `rope_theta` (5e6) and drops `rope_scaling`. + +**Equivalence**: text-only logits match the original VL model bit-for-bit in +fp32 (`max |logit diff| = 0.0` on a held-out prompt). + +Load with: + +```python +from transformers import AutoModelForCausalLM +model = AutoModelForCausalLM.from_pretrained("shushengyang/Qwen3-VL-2B-Instruct-LLM") +``` + +Produced by `personal/shusheng/mllm/misc/convert_qwen3vl_llm_to_qwen3.py` +(amilabs monorepo); intended as an LLM initialization for ScaleWM MLLM +experiments (vision-language-pretrained LLM vs text-only Qwen3-1.7B). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1243868 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# 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' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\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..81fa89a --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "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": 2048, + "initializer_range": 0.02, + "intermediate_size": 6144, + "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" + ], + "max_position_embeddings": 262144, + "max_window_layers": 28, + "model_type": "qwen3", + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_theta": 5000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.8.1", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..b0c710e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "repetition_penalty": 1.0, + "temperature": 0.7, + "top_k": 20, + "top_p": 0.8, + "transformers_version": "5.8.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..4437ad7 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f0e378ab92c9687d1ae4433a204a1b090d812c37e1ccb796f1009525dbb2a1f +size 3441185608 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..c7afbed --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506 +size 11422650 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ad641f7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "local_files_only": true, + "model_max_length": 262144, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}