deskmind/eyes-4b
hf deskmind/eyes-4b 2 sources, 2 claims · Watch
What each source says
| Property | Source | Said | Means here | ||||||
|---|---|---|---|---|---|---|---|---|---|
| Author author not compared | GGUF quantisations | mradermacherreceipt
What the source handed over{
"_id": "6abec05f9fc5cea9461921a9",
"author": "mradermacher",
"cardData": {
"base_model": "deskmind/eyes-4b",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": {
"readme_rev": 1
},
"quantized_by": "mradermacher",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"createdAt": "2026-10-01T20:19:43.000Z",
"downloads": 388,
"gated": false,
"id": "mradermacher/eyes-4b-GGUF",
"lastModified": "2026-10-01T20:41:17.000Z",
"library_name": "transformers",
"likes": 0,
"modelId": "mradermacher/eyes-4b-GGUF",
"private": false,
"sha": "40cb09c581f1da9dbe2151c2d36e02bca37649d8",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "eyes-4b.IQ4_XS.gguf"
},
{
"rfilename": "eyes-4b.Q2_K.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_L.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q6_K.gguf"
},
{
"rfilename": "eyes-4b.Q8_0.gguf"
},
{
"rfilename": "eyes-4b.f16.gguf"
},
{
"rfilename": "eyes-4b.mmproj-Q8_0.gguf"
},
{
"rfilename": "eyes-4b.mmproj-f16.gguf"
}
],
"tags": [
"transformers",
"gguf",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"en",
"zh",
"base_model:deskmind/eyes-4b",
"base_model:quantized:deskmind/eyes-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||||
| Author author not compared | Hugging Face models | deskmindreceipt
What the source handed over{
"_asked": "deskmind/eyes-4b",
"_id": "6ab93d2f206f30c91b7d78dd",
"author": "deskmind",
"cardData": {
"base_model": "mPLUG/GUI-Owl-1.5-4B-Instruct",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"model_type": "qwen3_vl",
"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
}
},
"createdAt": "2026-09-27T15:58:39.000Z",
"disabled": false,
"downloads": 32,
"gated": false,
"id": "deskmind/eyes-4b",
"lastModified": "2026-10-01T17:49:19.000Z",
"library_name": "transformers",
"likes": 0,
"model-index": null,
"modelId": "deskmind/eyes-4b",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 4826771968
},
"total": 4826771968
},
"sha": "55fdbc623b17f306eb2e0dc2489d032a4e2121b5",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration.json"
},
{
"rfilename": "eyes-4b-bf16.sha256"
},
{
"rfilename": "generation_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": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"conversational",
"en",
"zh",
"base_model:mPLUG/GUI-Owl-1.5-4B-Instruct",
"base_model:finetune:mPLUG/GUI-Owl-1.5-4B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 12977609899,
"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."
}
]
} | — | ||||||
| Base base | GGUF quantisations | deskmind/eyes-4breceipt
What the source handed over{
"_id": "6abec05f9fc5cea9461921a9",
"author": "mradermacher",
"cardData": {
"base_model": "deskmind/eyes-4b",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": {
"readme_rev": 1
},
"quantized_by": "mradermacher",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"createdAt": "2026-10-01T20:19:43.000Z",
"downloads": 388,
"gated": false,
"id": "mradermacher/eyes-4b-GGUF",
"lastModified": "2026-10-01T20:41:17.000Z",
"library_name": "transformers",
"likes": 0,
"modelId": "mradermacher/eyes-4b-GGUF",
"private": false,
"sha": "40cb09c581f1da9dbe2151c2d36e02bca37649d8",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "eyes-4b.IQ4_XS.gguf"
},
{
"rfilename": "eyes-4b.Q2_K.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_L.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q6_K.gguf"
},
{
"rfilename": "eyes-4b.Q8_0.gguf"
},
{
"rfilename": "eyes-4b.f16.gguf"
},
{
"rfilename": "eyes-4b.mmproj-Q8_0.gguf"
},
{
"rfilename": "eyes-4b.mmproj-f16.gguf"
}
],
"tags": [
"transformers",
"gguf",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"en",
"zh",
"base_model:deskmind/eyes-4b",
"base_model:quantized:deskmind/eyes-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||||
| Downloads downloads not compared | GGUF quantisations | 388receipt
What the source handed over{
"_id": "6abec05f9fc5cea9461921a9",
"author": "mradermacher",
"cardData": {
"base_model": "deskmind/eyes-4b",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": {
"readme_rev": 1
},
"quantized_by": "mradermacher",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"createdAt": "2026-10-01T20:19:43.000Z",
"downloads": 388,
"gated": false,
"id": "mradermacher/eyes-4b-GGUF",
"lastModified": "2026-10-01T20:41:17.000Z",
"library_name": "transformers",
"likes": 0,
"modelId": "mradermacher/eyes-4b-GGUF",
"private": false,
"sha": "40cb09c581f1da9dbe2151c2d36e02bca37649d8",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "eyes-4b.IQ4_XS.gguf"
},
{
"rfilename": "eyes-4b.Q2_K.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_L.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q6_K.gguf"
},
{
"rfilename": "eyes-4b.Q8_0.gguf"
},
{
"rfilename": "eyes-4b.f16.gguf"
},
{
"rfilename": "eyes-4b.mmproj-Q8_0.gguf"
},
{
"rfilename": "eyes-4b.mmproj-f16.gguf"
}
],
"tags": [
"transformers",
"gguf",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"en",
"zh",
"base_model:deskmind/eyes-4b",
"base_model:quantized:deskmind/eyes-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||||
| Downloads downloads not compared | Hugging Face models | 32receipt
What the source handed over{
"_asked": "deskmind/eyes-4b",
"_id": "6ab93d2f206f30c91b7d78dd",
"author": "deskmind",
"cardData": {
"base_model": "mPLUG/GUI-Owl-1.5-4B-Instruct",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"model_type": "qwen3_vl",
"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
}
},
"createdAt": "2026-09-27T15:58:39.000Z",
"disabled": false,
"downloads": 32,
"gated": false,
"id": "deskmind/eyes-4b",
"lastModified": "2026-10-01T17:49:19.000Z",
"library_name": "transformers",
"likes": 0,
"model-index": null,
"modelId": "deskmind/eyes-4b",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 4826771968
},
"total": 4826771968
},
"sha": "55fdbc623b17f306eb2e0dc2489d032a4e2121b5",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration.json"
},
{
"rfilename": "eyes-4b-bf16.sha256"
},
{
"rfilename": "generation_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": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"conversational",
"en",
"zh",
"base_model:mPLUG/GUI-Owl-1.5-4B-Instruct",
"base_model:finetune:mPLUG/GUI-Owl-1.5-4B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 12977609899,
"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 gated | Hugging Face models | falsereceipt
What the source handed over{
"_asked": "deskmind/eyes-4b",
"_id": "6ab93d2f206f30c91b7d78dd",
"author": "deskmind",
"cardData": {
"base_model": "mPLUG/GUI-Owl-1.5-4B-Instruct",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"model_type": "qwen3_vl",
"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
}
},
"createdAt": "2026-09-27T15:58:39.000Z",
"disabled": false,
"downloads": 32,
"gated": false,
"id": "deskmind/eyes-4b",
"lastModified": "2026-10-01T17:49:19.000Z",
"library_name": "transformers",
"likes": 0,
"model-index": null,
"modelId": "deskmind/eyes-4b",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 4826771968
},
"total": 4826771968
},
"sha": "55fdbc623b17f306eb2e0dc2489d032a4e2121b5",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration.json"
},
{
"rfilename": "eyes-4b-bf16.sha256"
},
{
"rfilename": "generation_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": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"conversational",
"en",
"zh",
"base_model:mPLUG/GUI-Owl-1.5-4B-Instruct",
"base_model:finetune:mPLUG/GUI-Owl-1.5-4B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 12977609899,
"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 licence | GGUF quantisations | apache-2.0receipt
What the source handed over{
"_id": "6abec05f9fc5cea9461921a9",
"author": "mradermacher",
"cardData": {
"base_model": "deskmind/eyes-4b",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": {
"readme_rev": 1
},
"quantized_by": "mradermacher",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"createdAt": "2026-10-01T20:19:43.000Z",
"downloads": 388,
"gated": false,
"id": "mradermacher/eyes-4b-GGUF",
"lastModified": "2026-10-01T20:41:17.000Z",
"library_name": "transformers",
"likes": 0,
"modelId": "mradermacher/eyes-4b-GGUF",
"private": false,
"sha": "40cb09c581f1da9dbe2151c2d36e02bca37649d8",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "eyes-4b.IQ4_XS.gguf"
},
{
"rfilename": "eyes-4b.Q2_K.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_L.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q6_K.gguf"
},
{
"rfilename": "eyes-4b.Q8_0.gguf"
},
{
"rfilename": "eyes-4b.f16.gguf"
},
{
"rfilename": "eyes-4b.mmproj-Q8_0.gguf"
},
{
"rfilename": "eyes-4b.mmproj-f16.gguf"
}
],
"tags": [
"transformers",
"gguf",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"en",
"zh",
"base_model:deskmind/eyes-4b",
"base_model:quantized:deskmind/eyes-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||||
| Licence licence | Hugging Face models | apache-2.0receipt
What the source handed over{
"_asked": "deskmind/eyes-4b",
"_id": "6ab93d2f206f30c91b7d78dd",
"author": "deskmind",
"cardData": {
"base_model": "mPLUG/GUI-Owl-1.5-4B-Instruct",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"model_type": "qwen3_vl",
"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
}
},
"createdAt": "2026-09-27T15:58:39.000Z",
"disabled": false,
"downloads": 32,
"gated": false,
"id": "deskmind/eyes-4b",
"lastModified": "2026-10-01T17:49:19.000Z",
"library_name": "transformers",
"likes": 0,
"model-index": null,
"modelId": "deskmind/eyes-4b",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 4826771968
},
"total": 4826771968
},
"sha": "55fdbc623b17f306eb2e0dc2489d032a4e2121b5",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration.json"
},
{
"rfilename": "eyes-4b-bf16.sha256"
},
{
"rfilename": "generation_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": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"conversational",
"en",
"zh",
"base_model:mPLUG/GUI-Owl-1.5-4B-Instruct",
"base_model:finetune:mPLUG/GUI-Owl-1.5-4B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 12977609899,
"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 likes | GGUF quantisations | 0receipt
What the source handed over{
"_id": "6abec05f9fc5cea9461921a9",
"author": "mradermacher",
"cardData": {
"base_model": "deskmind/eyes-4b",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"mradermacher": {
"readme_rev": 1
},
"quantized_by": "mradermacher",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"createdAt": "2026-10-01T20:19:43.000Z",
"downloads": 388,
"gated": false,
"id": "mradermacher/eyes-4b-GGUF",
"lastModified": "2026-10-01T20:41:17.000Z",
"library_name": "transformers",
"likes": 0,
"modelId": "mradermacher/eyes-4b-GGUF",
"private": false,
"sha": "40cb09c581f1da9dbe2151c2d36e02bca37649d8",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "README.md"
},
{
"rfilename": "eyes-4b.IQ4_XS.gguf"
},
{
"rfilename": "eyes-4b.Q2_K.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_L.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q3_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q4_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_M.gguf"
},
{
"rfilename": "eyes-4b.Q5_K_S.gguf"
},
{
"rfilename": "eyes-4b.Q6_K.gguf"
},
{
"rfilename": "eyes-4b.Q8_0.gguf"
},
{
"rfilename": "eyes-4b.f16.gguf"
},
{
"rfilename": "eyes-4b.mmproj-Q8_0.gguf"
},
{
"rfilename": "eyes-4b.mmproj-f16.gguf"
}
],
"tags": [
"transformers",
"gguf",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"en",
"zh",
"base_model:deskmind/eyes-4b",
"base_model:quantized:deskmind/eyes-4b",
"license:apache-2.0",
"endpoints_compatible",
"region:us",
"conversational"
]
} | — | ||||||
| Likes likes | Hugging Face models | 0receipt
What the source handed over{
"_asked": "deskmind/eyes-4b",
"_id": "6ab93d2f206f30c91b7d78dd",
"author": "deskmind",
"cardData": {
"base_model": "mPLUG/GUI-Owl-1.5-4B-Instruct",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"model_type": "qwen3_vl",
"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
}
},
"createdAt": "2026-09-27T15:58:39.000Z",
"disabled": false,
"downloads": 32,
"gated": false,
"id": "deskmind/eyes-4b",
"lastModified": "2026-10-01T17:49:19.000Z",
"library_name": "transformers",
"likes": 0,
"model-index": null,
"modelId": "deskmind/eyes-4b",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 4826771968
},
"total": 4826771968
},
"sha": "55fdbc623b17f306eb2e0dc2489d032a4e2121b5",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration.json"
},
{
"rfilename": "eyes-4b-bf16.sha256"
},
{
"rfilename": "generation_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": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"conversational",
"en",
"zh",
"base_model:mPLUG/GUI-Owl-1.5-4B-Instruct",
"base_model:finetune:mPLUG/GUI-Owl-1.5-4B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 12977609899,
"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 task | Hugging Face models | image-text-to-textreceipt
What the source handed over{
"_asked": "deskmind/eyes-4b",
"_id": "6ab93d2f206f30c91b7d78dd",
"author": "deskmind",
"cardData": {
"base_model": "mPLUG/GUI-Owl-1.5-4B-Instruct",
"language": [
"en",
"zh"
],
"library_name": "transformers",
"license": "apache-2.0",
"pipeline_tag": "image-text-to-text",
"tags": [
"deskmind",
"gui-grounding",
"computer-use",
"screenspot"
]
},
"config": {
"architectures": [
"Qwen3VLForConditionalGeneration"
],
"model_type": "qwen3_vl",
"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
}
},
"createdAt": "2026-09-27T15:58:39.000Z",
"disabled": false,
"downloads": 32,
"gated": false,
"id": "deskmind/eyes-4b",
"lastModified": "2026-10-01T17:49:19.000Z",
"library_name": "transformers",
"likes": 0,
"model-index": null,
"modelId": "deskmind/eyes-4b",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 4826771968
},
"total": 4826771968
},
"sha": "55fdbc623b17f306eb2e0dc2489d032a4e2121b5",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.json"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration.json"
},
{
"rfilename": "eyes-4b-bf16.sha256"
},
{
"rfilename": "generation_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": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen3_vl",
"image-text-to-text",
"deskmind",
"gui-grounding",
"computer-use",
"screenspot",
"conversational",
"en",
"zh",
"base_model:mPLUG/GUI-Owl-1.5-4B-Instruct",
"base_model:finetune:mPLUG/GUI-Owl-1.5-4B-Instruct",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 12977609899,
"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
| deskmind/eyes-4b zetlyn/models-hf · 2026-09-27 | author deskmind downloads 32 gated false licence apache-2.0 likes 0 task image-text-to-text | source |
quantisation
| mradermacher/eyes-4b-GGUF zetlyn/models-gguf · 2026-10-01 | author mradermacher base deskmind/eyes-4b downloads 388 licence apache-2.0 likes 0 | source |