ByteDance-Seed/UI-TARS-2B-SFT
zetlyn/models-hf model hf ByteDance-Seed/UI-TARS-2B-SFT known 2025-01-20
https://huggingface.co/ByteDance-Seed/UI-TARS-2B-SFT
Properties
| author | ByteDance-Seedreceipt
What the source handed over{
"_asked": "ByteDance-Seed/UI-TARS-2B-SFT",
"_id": "678db3a76e06f11c16cfff5d",
"author": "ByteDance-Seed",
"cardData": {
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"gui"
]
},
"config": {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"model_type": "qwen2_vl",
"processor_config": {
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
},
"tokenizer_config": {
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-01-20T02:23:35.000Z",
"disabled": false,
"downloads": 3906,
"gated": false,
"id": "ByteDance-Seed/UI-TARS-2B-SFT",
"lastModified": "2025-01-25T15:03:35.000Z",
"library_name": "transformers",
"likes": 39,
"model-index": null,
"modelId": "ByteDance-Seed/UI-TARS-2B-SFT",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 2442359296
},
"total": 2442359296
},
"sha": "f366a1db3e7f29635f5b236d6a71dea367a0a700",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"ravinder012/visual",
"baqr/computer_use_ootb"
],
"tags": [
"transformers",
"safetensors",
"qwen2_vl",
"image-text-to-text",
"multimodal",
"gui",
"conversational",
"en",
"arxiv:2501.12326",
"license:apache-2.0",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 9780936723,
"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."
}
]
} | ||||||
|---|---|---|---|---|---|---|---|
| downloads | 3906receipt
What the source handed over{
"_asked": "ByteDance-Seed/UI-TARS-2B-SFT",
"_id": "678db3a76e06f11c16cfff5d",
"author": "ByteDance-Seed",
"cardData": {
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"gui"
]
},
"config": {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"model_type": "qwen2_vl",
"processor_config": {
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
},
"tokenizer_config": {
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-01-20T02:23:35.000Z",
"disabled": false,
"downloads": 3906,
"gated": false,
"id": "ByteDance-Seed/UI-TARS-2B-SFT",
"lastModified": "2025-01-25T15:03:35.000Z",
"library_name": "transformers",
"likes": 39,
"model-index": null,
"modelId": "ByteDance-Seed/UI-TARS-2B-SFT",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 2442359296
},
"total": 2442359296
},
"sha": "f366a1db3e7f29635f5b236d6a71dea367a0a700",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"ravinder012/visual",
"baqr/computer_use_ootb"
],
"tags": [
"transformers",
"safetensors",
"qwen2_vl",
"image-text-to-text",
"multimodal",
"gui",
"conversational",
"en",
"arxiv:2501.12326",
"license:apache-2.0",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 9780936723,
"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."
}
]
} | ||||||
| gated | falsereceipt
What the source handed over{
"_asked": "ByteDance-Seed/UI-TARS-2B-SFT",
"_id": "678db3a76e06f11c16cfff5d",
"author": "ByteDance-Seed",
"cardData": {
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"gui"
]
},
"config": {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"model_type": "qwen2_vl",
"processor_config": {
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
},
"tokenizer_config": {
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-01-20T02:23:35.000Z",
"disabled": false,
"downloads": 3906,
"gated": false,
"id": "ByteDance-Seed/UI-TARS-2B-SFT",
"lastModified": "2025-01-25T15:03:35.000Z",
"library_name": "transformers",
"likes": 39,
"model-index": null,
"modelId": "ByteDance-Seed/UI-TARS-2B-SFT",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 2442359296
},
"total": 2442359296
},
"sha": "f366a1db3e7f29635f5b236d6a71dea367a0a700",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"ravinder012/visual",
"baqr/computer_use_ootb"
],
"tags": [
"transformers",
"safetensors",
"qwen2_vl",
"image-text-to-text",
"multimodal",
"gui",
"conversational",
"en",
"arxiv:2501.12326",
"license:apache-2.0",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 9780936723,
"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."
}
]
} | ||||||
| licence | apache-2.0receipt
What the source handed over{
"_asked": "ByteDance-Seed/UI-TARS-2B-SFT",
"_id": "678db3a76e06f11c16cfff5d",
"author": "ByteDance-Seed",
"cardData": {
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"gui"
]
},
"config": {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"model_type": "qwen2_vl",
"processor_config": {
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
},
"tokenizer_config": {
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-01-20T02:23:35.000Z",
"disabled": false,
"downloads": 3906,
"gated": false,
"id": "ByteDance-Seed/UI-TARS-2B-SFT",
"lastModified": "2025-01-25T15:03:35.000Z",
"library_name": "transformers",
"likes": 39,
"model-index": null,
"modelId": "ByteDance-Seed/UI-TARS-2B-SFT",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 2442359296
},
"total": 2442359296
},
"sha": "f366a1db3e7f29635f5b236d6a71dea367a0a700",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"ravinder012/visual",
"baqr/computer_use_ootb"
],
"tags": [
"transformers",
"safetensors",
"qwen2_vl",
"image-text-to-text",
"multimodal",
"gui",
"conversational",
"en",
"arxiv:2501.12326",
"license:apache-2.0",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 9780936723,
"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."
}
]
} | ||||||
| likes | 39receipt
What the source handed over{
"_asked": "ByteDance-Seed/UI-TARS-2B-SFT",
"_id": "678db3a76e06f11c16cfff5d",
"author": "ByteDance-Seed",
"cardData": {
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"gui"
]
},
"config": {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"model_type": "qwen2_vl",
"processor_config": {
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
},
"tokenizer_config": {
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-01-20T02:23:35.000Z",
"disabled": false,
"downloads": 3906,
"gated": false,
"id": "ByteDance-Seed/UI-TARS-2B-SFT",
"lastModified": "2025-01-25T15:03:35.000Z",
"library_name": "transformers",
"likes": 39,
"model-index": null,
"modelId": "ByteDance-Seed/UI-TARS-2B-SFT",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 2442359296
},
"total": 2442359296
},
"sha": "f366a1db3e7f29635f5b236d6a71dea367a0a700",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"ravinder012/visual",
"baqr/computer_use_ootb"
],
"tags": [
"transformers",
"safetensors",
"qwen2_vl",
"image-text-to-text",
"multimodal",
"gui",
"conversational",
"en",
"arxiv:2501.12326",
"license:apache-2.0",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 9780936723,
"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."
}
]
} | ||||||
| task | image-text-to-textreceipt
What the source handed over{
"_asked": "ByteDance-Seed/UI-TARS-2B-SFT",
"_id": "678db3a76e06f11c16cfff5d",
"author": "ByteDance-Seed",
"cardData": {
"language": [
"en"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"multimodal",
"gui"
]
},
"config": {
"architectures": [
"Qwen2VLForConditionalGeneration"
],
"model_type": "qwen2_vl",
"processor_config": {
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
},
"tokenizer_config": {
"bos_token": null,
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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 %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2025-01-20T02:23:35.000Z",
"disabled": false,
"downloads": 3906,
"gated": false,
"id": "ByteDance-Seed/UI-TARS-2B-SFT",
"lastModified": "2025-01-25T15:03:35.000Z",
"library_name": "transformers",
"likes": 39,
"model-index": null,
"modelId": "ByteDance-Seed/UI-TARS-2B-SFT",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"F32": 2442359296
},
"total": 2442359296
},
"sha": "f366a1db3e7f29635f5b236d6a71dea367a0a700",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"ravinder012/visual",
"baqr/computer_use_ootb"
],
"tags": [
"transformers",
"safetensors",
"qwen2_vl",
"image-text-to-text",
"multimodal",
"gui",
"conversational",
"en",
"arxiv:2501.12326",
"license:apache-2.0",
"eval-results",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 9780936723,
"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."
}
]
} |
Text
This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/ByteDance-Seed/UI-TARS-2B-SFT.