DeepCybo/PhysBrain1.5-8B
zetlyn/models-hf model hf DeepCybo/PhysBrain1.5-8B known 2026-09-08
https://huggingface.co/DeepCybo/PhysBrain1.5-8B
Properties
| author | DeepCyboreceipt
What the source handed over{
"_asked": "DeepCybo/PhysBrain1.5-8B",
"_id": "6aa03df7b90ab2d48d74b9b0",
"author": "DeepCybo",
"cardData": {
"base_model": [
"Qwen/Qwen3-VL-8B-Instruct"
],
"language": [
"en",
"zh"
],
"library_name": "transformers",
"pipeline_tag": "any-to-any",
"tags": [
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"chat_template_jinja": "{%- 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",
"model_type": "qwen3_vl",
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-09-08T16:55:19.000Z",
"disabled": false,
"downloads": 849,
"gated": false,
"id": "DeepCybo/PhysBrain1.5-8B",
"lastModified": "2026-09-16T03:43:50.000Z",
"library_name": "transformers",
"likes": 28,
"model-index": null,
"modelId": "DeepCybo/PhysBrain1.5-8B",
"pipeline_tag": "any-to-any",
"private": false,
"safetensors": {
"parameters": {
"BF16": 8903438576
},
"total": 8903438576
},
"sha": "a81fdfe04712084d008154cee53ed2b62775563b",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "assets/.DS_Store"
},
{
"rfilename": "assets/case-action-trajectory.png"
},
{
"rfilename": "assets/case-future-prediction-v2.png"
},
{
"rfilename": "assets/case-future-prediction.png"
},
{
"rfilename": "assets/embodied_benchmarks.png"
},
{
"rfilename": "assets/evaluation-cases-v6.png"
},
{
"rfilename": "assets/leaderboard.svg"
},
{
"rfilename": "assets/logo.png"
},
{
"rfilename": "assets/model-architecture-v2.png"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"DeepCybo/physbrain1-5-8b-demo"
],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal",
"any-to-any",
"en",
"zh",
"arxiv:2609.14973",
"base_model:Qwen/Qwen3-VL-8B-Instruct",
"base_model:finetune:Qwen/Qwen3-VL-8B-Instruct",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 17831537098
} | ||||||
|---|---|---|---|---|---|---|---|
| downloads | 849receipt
What the source handed over{
"_asked": "DeepCybo/PhysBrain1.5-8B",
"_id": "6aa03df7b90ab2d48d74b9b0",
"author": "DeepCybo",
"cardData": {
"base_model": [
"Qwen/Qwen3-VL-8B-Instruct"
],
"language": [
"en",
"zh"
],
"library_name": "transformers",
"pipeline_tag": "any-to-any",
"tags": [
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"chat_template_jinja": "{%- 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",
"model_type": "qwen3_vl",
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-09-08T16:55:19.000Z",
"disabled": false,
"downloads": 849,
"gated": false,
"id": "DeepCybo/PhysBrain1.5-8B",
"lastModified": "2026-09-16T03:43:50.000Z",
"library_name": "transformers",
"likes": 28,
"model-index": null,
"modelId": "DeepCybo/PhysBrain1.5-8B",
"pipeline_tag": "any-to-any",
"private": false,
"safetensors": {
"parameters": {
"BF16": 8903438576
},
"total": 8903438576
},
"sha": "a81fdfe04712084d008154cee53ed2b62775563b",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "assets/.DS_Store"
},
{
"rfilename": "assets/case-action-trajectory.png"
},
{
"rfilename": "assets/case-future-prediction-v2.png"
},
{
"rfilename": "assets/case-future-prediction.png"
},
{
"rfilename": "assets/embodied_benchmarks.png"
},
{
"rfilename": "assets/evaluation-cases-v6.png"
},
{
"rfilename": "assets/leaderboard.svg"
},
{
"rfilename": "assets/logo.png"
},
{
"rfilename": "assets/model-architecture-v2.png"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"DeepCybo/physbrain1-5-8b-demo"
],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal",
"any-to-any",
"en",
"zh",
"arxiv:2609.14973",
"base_model:Qwen/Qwen3-VL-8B-Instruct",
"base_model:finetune:Qwen/Qwen3-VL-8B-Instruct",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 17831537098
} | ||||||
| gated | falsereceipt
What the source handed over{
"_asked": "DeepCybo/PhysBrain1.5-8B",
"_id": "6aa03df7b90ab2d48d74b9b0",
"author": "DeepCybo",
"cardData": {
"base_model": [
"Qwen/Qwen3-VL-8B-Instruct"
],
"language": [
"en",
"zh"
],
"library_name": "transformers",
"pipeline_tag": "any-to-any",
"tags": [
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"chat_template_jinja": "{%- 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",
"model_type": "qwen3_vl",
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-09-08T16:55:19.000Z",
"disabled": false,
"downloads": 849,
"gated": false,
"id": "DeepCybo/PhysBrain1.5-8B",
"lastModified": "2026-09-16T03:43:50.000Z",
"library_name": "transformers",
"likes": 28,
"model-index": null,
"modelId": "DeepCybo/PhysBrain1.5-8B",
"pipeline_tag": "any-to-any",
"private": false,
"safetensors": {
"parameters": {
"BF16": 8903438576
},
"total": 8903438576
},
"sha": "a81fdfe04712084d008154cee53ed2b62775563b",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "assets/.DS_Store"
},
{
"rfilename": "assets/case-action-trajectory.png"
},
{
"rfilename": "assets/case-future-prediction-v2.png"
},
{
"rfilename": "assets/case-future-prediction.png"
},
{
"rfilename": "assets/embodied_benchmarks.png"
},
{
"rfilename": "assets/evaluation-cases-v6.png"
},
{
"rfilename": "assets/leaderboard.svg"
},
{
"rfilename": "assets/logo.png"
},
{
"rfilename": "assets/model-architecture-v2.png"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"DeepCybo/physbrain1-5-8b-demo"
],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal",
"any-to-any",
"en",
"zh",
"arxiv:2609.14973",
"base_model:Qwen/Qwen3-VL-8B-Instruct",
"base_model:finetune:Qwen/Qwen3-VL-8B-Instruct",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 17831537098
} | ||||||
| likes | 28receipt
What the source handed over{
"_asked": "DeepCybo/PhysBrain1.5-8B",
"_id": "6aa03df7b90ab2d48d74b9b0",
"author": "DeepCybo",
"cardData": {
"base_model": [
"Qwen/Qwen3-VL-8B-Instruct"
],
"language": [
"en",
"zh"
],
"library_name": "transformers",
"pipeline_tag": "any-to-any",
"tags": [
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"chat_template_jinja": "{%- 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",
"model_type": "qwen3_vl",
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-09-08T16:55:19.000Z",
"disabled": false,
"downloads": 849,
"gated": false,
"id": "DeepCybo/PhysBrain1.5-8B",
"lastModified": "2026-09-16T03:43:50.000Z",
"library_name": "transformers",
"likes": 28,
"model-index": null,
"modelId": "DeepCybo/PhysBrain1.5-8B",
"pipeline_tag": "any-to-any",
"private": false,
"safetensors": {
"parameters": {
"BF16": 8903438576
},
"total": 8903438576
},
"sha": "a81fdfe04712084d008154cee53ed2b62775563b",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "assets/.DS_Store"
},
{
"rfilename": "assets/case-action-trajectory.png"
},
{
"rfilename": "assets/case-future-prediction-v2.png"
},
{
"rfilename": "assets/case-future-prediction.png"
},
{
"rfilename": "assets/embodied_benchmarks.png"
},
{
"rfilename": "assets/evaluation-cases-v6.png"
},
{
"rfilename": "assets/leaderboard.svg"
},
{
"rfilename": "assets/logo.png"
},
{
"rfilename": "assets/model-architecture-v2.png"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"DeepCybo/physbrain1-5-8b-demo"
],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal",
"any-to-any",
"en",
"zh",
"arxiv:2609.14973",
"base_model:Qwen/Qwen3-VL-8B-Instruct",
"base_model:finetune:Qwen/Qwen3-VL-8B-Instruct",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 17831537098
} | ||||||
| task | any-to-anyreceipt
What the source handed over{
"_asked": "DeepCybo/PhysBrain1.5-8B",
"_id": "6aa03df7b90ab2d48d74b9b0",
"author": "DeepCybo",
"cardData": {
"base_model": [
"Qwen/Qwen3-VL-8B-Instruct"
],
"language": [
"en",
"zh"
],
"library_name": "transformers",
"pipeline_tag": "any-to-any",
"tags": [
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"chat_template_jinja": "{%- 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",
"model_type": "qwen3_vl",
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-09-08T16:55:19.000Z",
"disabled": false,
"downloads": 849,
"gated": false,
"id": "DeepCybo/PhysBrain1.5-8B",
"lastModified": "2026-09-16T03:43:50.000Z",
"library_name": "transformers",
"likes": 28,
"model-index": null,
"modelId": "DeepCybo/PhysBrain1.5-8B",
"pipeline_tag": "any-to-any",
"private": false,
"safetensors": {
"parameters": {
"BF16": 8903438576
},
"total": 8903438576
},
"sha": "a81fdfe04712084d008154cee53ed2b62775563b",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "assets/.DS_Store"
},
{
"rfilename": "assets/case-action-trajectory.png"
},
{
"rfilename": "assets/case-future-prediction-v2.png"
},
{
"rfilename": "assets/case-future-prediction.png"
},
{
"rfilename": "assets/embodied_benchmarks.png"
},
{
"rfilename": "assets/evaluation-cases-v6.png"
},
{
"rfilename": "assets/leaderboard.svg"
},
{
"rfilename": "assets/logo.png"
},
{
"rfilename": "assets/model-architecture-v2.png"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "model-00001-of-00004.safetensors"
},
{
"rfilename": "model-00002-of-00004.safetensors"
},
{
"rfilename": "model-00003-of-00004.safetensors"
},
{
"rfilename": "model-00004-of-00004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"DeepCybo/physbrain1-5-8b-demo"
],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"embodied-ai",
"vision-language-model",
"robotics",
"spatial-reasoning",
"multimodal",
"any-to-any",
"en",
"zh",
"arxiv:2609.14973",
"base_model:Qwen/Qwen3-VL-8B-Instruct",
"base_model:finetune:Qwen/Qwen3-VL-8B-Instruct",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 17831537098
} |
Text
This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/DeepCybo/PhysBrain1.5-8B.