Image-Text-to-Text
Transformers
Safetensors
GGUF
English
qwen2_5_vl
remyx
qwen2.5-vl
spatial-reasoning
multimodal
vlm
vqasynth
thinking
reasoning
test-time-compute
robotics
embodied-ai
quantitative-spatial-reasoning
distance-estimation
visual-question-answering
conversational
Eval Results
text-generation-inference
{ | |
"additional_special_tokens": [ | |
"<|im_start|>", | |
"<|im_end|>", | |
"<|object_ref_start|>", | |
"<|object_ref_end|>", | |
"<|box_start|>", | |
"<|box_end|>", | |
"<|quad_start|>", | |
"<|quad_end|>", | |
"<|vision_start|>", | |
"<|vision_end|>", | |
"<|vision_pad|>", | |
"<|image_pad|>", | |
"<|video_pad|>" | |
], | |
"eos_token": { | |
"content": "<|im_end|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
}, | |
"pad_token": { | |
"content": "<|endoftext|>", | |
"lstrip": false, | |
"normalized": false, | |
"rstrip": false, | |
"single_word": false | |
} | |
} | |