{"_id":"68d0c878f7dc520a235be3c5","id":"Qwen/Qwen3-VL-235B-A22B-Instruct","private":false,"pipeline_tag":"image-text-to-text","library_name":"transformers","tags":["transformers","safetensors","qwen3_vl_moe","image-text-to-text","conversational","arxiv:2505.09388","arxiv:2502.13923","arxiv:2409.12191","arxiv:2308.12966","license:apache-2.0","eval-results","endpoints_compatible","deploy:azure","region:us"],"downloads":304805,"likes":420,"modelId":"Qwen/Qwen3-VL-235B-A22B-Instruct","author":"Qwen","sha":"710c13861be6c466e66de3f484069440b8f31389","lastModified":"2025-11-26T13:18:18.000Z","gated":false,"disabled":false,"widgetData":[{"text":"Hi, what can you help me with?"},{"text":"What is 84 * 3 / 2?"},{"text":"Tell me an interesting fact about the universe!"},{"text":"Explain quantum computing in simple terms."}],"model-index":null,"config":{"architectures":["Qwen3VLMoeForConditionalGeneration"],"model_type":"qwen3_vl_moe","processor_config":{"chat_template":"{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\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 <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\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</tool_call>' }}\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<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n"},"tokenizer_config":{"bos_token":null,"chat_template":"{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\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 <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' }}\n        {%- if messages[0].content is string %}\n            {{- messages[0].content }}\n        {%- else %}\n            {%- for content in messages[0].content %}\n                {%- if 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n    {%- if message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role + '\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content_item in message.content %}\n                {%- if 'text' in content_item %}\n                    {{- content_item.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and message.content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\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</tool_call>' }}\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<tool_response>\\n' }}\n        {%- if message.content is string %}\n            {{- message.content }}\n        {%- else %}\n            {%- for content in message.content %}\n                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n                    <|vision_start|><|image_pad|><|vision_end|>\n                {%- elif content.type == 'video' or 'video' in content %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n                    <|vision_start|><|video_pad|><|vision_end|>\n                {%- elif 'text' in content %}\n                    {{- content.text }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n","eos_token":"<|im_end|>","pad_token":"<|endoftext|>","unk_token":null}},"cardData":{"license":"apache-2.0","library_name":"transformers"},"transformersInfo":{"auto_model":"AutoModelForMultimodalLM","pipeline_tag":"image-text-to-text","processor":"AutoProcessor"},"siblings":[{"rfilename":".gitattributes"},{"rfilename":"README.md"},{"rfilename":"chat_template.json"},{"rfilename":"config.json"},{"rfilename":"generation_config.json"},{"rfilename":"merges.txt"},{"rfilename":"model-00001-of-00096.safetensors"},{"rfilename":"model-00002-of-00096.safetensors"},{"rfilename":"model-00003-of-00096.safetensors"},{"rfilename":"model-00004-of-00096.safetensors"},{"rfilename":"model-00005-of-00096.safetensors"},{"rfilename":"model-00006-of-00096.safetensors"},{"rfilename":"model-00007-of-00096.safetensors"},{"rfilename":"model-00008-of-00096.safetensors"},{"rfilename":"model-00009-of-00096.safetensors"},{"rfilename":"model-00010-of-00096.safetensors"},{"rfilename":"model-00011-of-00096.safetensors"},{"rfilename":"model-00012-of-00096.safetensors"},{"rfilename":"model-00013-of-00096.safetensors"},{"rfilename":"model-00014-of-00096.safetensors"},{"rfilename":"model-00015-of-00096.safetensors"},{"rfilename":"model-00016-of-00096.safetensors"},{"rfilename":"model-00017-of-00096.safetensors"},{"rfilename":"model-00018-of-00096.safetensors"},{"rfilename":"model-00019-of-00096.safetensors"},{"rfilename":"model-00020-of-00096.safetensors"},{"rfilename":"model-00021-of-00096.safetensors"},{"rfilename":"model-00022-of-00096.safetensors"},{"rfilename":"model-00023-of-00096.safetensors"},{"rfilename":"model-00024-of-00096.safetensors"},{"rfilename":"model-00025-of-00096.safetensors"},{"rfilename":"model-00026-of-00096.safetensors"},{"rfilename":"model-00027-of-00096.safetensors"},{"rfilename":"model-00028-of-00096.safetensors"},{"rfilename":"model-00029-of-00096.safetensors"},{"rfilename":"model-00030-of-00096.safetensors"},{"rfilename":"model-00031-of-00096.safetensors"},{"rfilename":"model-00032-of-00096.safetensors"},{"rfilename":"model-00033-of-00096.safetensors"},{"rfilename":"model-00034-of-00096.safetensors"},{"rfilename":"model-00035-of-00096.safetensors"},{"rfilename":"model-00036-of-00096.safetensors"},{"rfilename":"model-00037-of-00096.safetensors"},{"rfilename":"model-00038-of-00096.safetensors"},{"rfilename":"model-00039-of-00096.safetensors"},{"rfilename":"model-00040-of-00096.safetensors"},{"rfilename":"model-00041-of-00096.safetensors"},{"rfilename":"model-00042-of-00096.safetensors"},{"rfilename":"model-00043-of-00096.safetensors"},{"rfilename":"model-00044-of-00096.safetensors"},{"rfilename":"model-00045-of-00096.safetensors"},{"rfilename":"model-00046-of-00096.safetensors"},{"rfilename":"model-00047-of-00096.safetensors"},{"rfilename":"model-00048-of-00096.safetensors"},{"rfilename":"model-00049-of-00096.safetensors"},{"rfilename":"model-00050-of-00096.safetensors"},{"rfilename":"model-00051-of-00096.safetensors"},{"rfilename":"model-00052-of-00096.safetensors"},{"rfilename":"model-00053-of-00096.safetensors"},{"rfilename":"model-00054-of-00096.safetensors"},{"rfilename":"model-00055-of-00096.safetensors"},{"rfilename":"model-00056-of-00096.safetensors"},{"rfilename":"model-00057-of-00096.safetensors"},{"rfilename":"model-00058-of-00096.safetensors"},{"rfilename":"model-00059-of-00096.safetensors"},{"rfilename":"model-00060-of-00096.safetensors"},{"rfilename":"model-00061-of-00096.safetensors"},{"rfilename":"model-00062-of-00096.safetensors"},{"rfilename":"model-00063-of-00096.safetensors"},{"rfilename":"model-00064-of-00096.safetensors"},{"rfilename":"model-00065-of-00096.safetensors"},{"rfilename":"model-00066-of-00096.safetensors"},{"rfilename":"model-00067-of-00096.safetensors"},{"rfilename":"model-00068-of-00096.safetensors"},{"rfilename":"model-00069-of-00096.safetensors"},{"rfilename":"model-00070-of-00096.safetensors"},{"rfilename":"model-00071-of-00096.safetensors"},{"rfilename":"model-00072-of-00096.safetensors"},{"rfilename":"model-00073-of-00096.safetensors"},{"rfilename":"model-00074-of-00096.safetensors"},{"rfilename":"model-00075-of-00096.safetensors"},{"rfilename":"model-00076-of-00096.safetensors"},{"rfilename":"model-00077-of-00096.safetensors"},{"rfilename":"model-00078-of-00096.safetensors"},{"rfilename":"model-00079-of-00096.safetensors"},{"rfilename":"model-00080-of-00096.safetensors"},{"rfilename":"model-00081-of-00096.safetensors"},{"rfilename":"model-00082-of-00096.safetensors"},{"rfilename":"model-00083-of-00096.safetensors"},{"rfilename":"model-00084-of-00096.safetensors"},{"rfilename":"model-00085-of-00096.safetensors"},{"rfilename":"model-00086-of-00096.safetensors"},{"rfilename":"model-00087-of-00096.safetensors"},{"rfilename":"model-00088-of-00096.safetensors"},{"rfilename":"model-00089-of-00096.safetensors"},{"rfilename":"model-00090-of-00096.safetensors"},{"rfilename":"model-00091-of-00096.safetensors"},{"rfilename":"model-00092-of-00096.safetensors"},{"rfilename":"model-00093-of-00096.safetensors"},{"rfilename":"model-00094-of-00096.safetensors"},{"rfilename":"model-00095-of-00096.safetensors"},{"rfilename":"model-00096-of-00096.safetensors"},{"rfilename":"model.safetensors.index.json"},{"rfilename":"preprocessor_config.json"},{"rfilename":"tokenizer.json"},{"rfilename":"tokenizer_config.json"},{"rfilename":"video_preprocessor_config.json"},{"rfilename":"vocab.json"}],"spaces":["tardellirs/model-pulse","embedl/hfviewer","aquanode/gpu-vram-calculator","ginigen-ai/open-router-leaderboard","lerobot/annotation-studio","hadadxyz/ai","umint/ai","smolagents/computer-use-agent","nvidia/Cosmos3-Action-Viewer","burtenshaw/qwen-atari","weathon/VSF","Elysia-Suite/elysia-markdown-studio","Elysia-Suite/elysia-code-companion","mpvasilis/CUA","Mmmma4iio/computer-use-agent","AdarshJi/FALTU_ADARSH","YuZijie123/myyy-woof","nvidia/Cosmos3-Action-Viewer-Prerelease","utarn/ai_ocr","kawaiipeace/AI-OMS-Analyze","bboat/AI-OMS-Analyze","malekradwan130/EbWFsZWtyYWR3YW4xMzBAZ21haWwuY","Murali-rade/final-gaia-agent","Nymbo/ChatMCP","drei22/Qwen-Qwen3-VL-235B-A22B-Instruct","dansam123/Qwen-Qwen3-VL-235B-A22B-Instruct","manicrmtest/Qwen-Qwen3-VL-235B-A22B-Instruct","Pritfort/Qwen-Qwen3-VL-235B-A22B-Instruct","00Boobs00/computer-use-agent","ijohn07/elysia-code-companion","ijohn07/elysia-markdown-studio","tog/GPUguesstimator","vakilrathod67/ai","superfluz/ai","Dar1us-Khan/ai","initial01/agent_course","chrissoria/CatLLM","joethuram/ai","capybara4996/flux2","Madras1/StrandDemo","amadsyufi/ai","charlieshawn/llm","damincordova/chat","CatLLM/survey-summarizer","ramirosolis/ai","inigovaldorin/ai","tariqimani/ai","magboola/qwen3vl-zerogpu","hikapi/ai","DamianRoss/ai","siakatara/ai","wilsonses/ai","hekergod11/AI-Playground","Kalibro/ai","SampleCraft/hi","SampleCraft/ai","wang468/ai","abarra/demo","Mdz87/ai","cassianrook/ai","Linacre/ai","LuisJeRU/ai","Maher12345/ai","justinhearn/ai","timiu999/ai","AdarshJi/DDS","AdarshJi/MD","VikVib/ai","nonuu/hand2excal","AdarshJi/IMGDEPLOY","Adedoyinjames/Ladybug","Saksak65/ai","Saksak65/Chat","LogitCode/FlexChat","LogitCode/FlexChat-Gold","LogitCode/FlexChat-Warm","LogitCode/FlexChat-terminal","LogitCode/FlexChat-blue","yrawal2004/file_upload_test","intelkishan/qwen-atari","yuan111556/ai","yrawal2004/Metadata_Re-enrichment","umar2/cortex-router","shmr90661/haven-ai-backend","Devil200501/ai","gdfgdgdfghghyt/ai","hacktogone/cadrimages-saas","artmyvibe/art-my-vibe-api","Ademhi090/computer-use-agent","faizan24/Text_Extraction","NextNeural/NINA","Hdhdhyd/computer-use-agent","Digital-FGV-Jr/backend-juninho","jaeiJJ/hf-inference-providers-demo","Fahad0saad/arabic-ocr-v2","Falln87/computer-use-agent","AbstractPhil/qwen-caption-array","kmistri070197/Final_Assignment_Template","ykumar2020/gaia-final-assignment","AlanaSky/Cosmos3-Action-Viewer"],"createdAt":"2025-09-22T03:54:32.000Z","safetensors":{"parameters":{"BF16":235670022896},"total":235670022896},"inference":"warm","usedStorage":471340223736}