Hugging Face's logo

Qwen
/
Qwen2.5-VL-7B-Instruct

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
image-to-text
multimodal
conversational
text-generation-inference
Model card Files
xet
Community
61

Confusion with the parameter fixed in visual ViT merger in source code.

#52
by Bytes-Lin - opened
Discussion
Bytes-Lin

The context_dim parameter seems wrong.

image.png

See details in: https://github.com/huggingface/transformers/issues/38889

Sign up or log in to comment