Hugging Face's logo

Qwen
/
Qwen2-VL-7B-Instruct

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_vl
multimodal
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
76

Mapping hidden states back to image patches

#68
by dbasu - opened
Discussion
dbasu

How can I map the hidden states back to each image patch in the input images assuming there were multiple input images in one call.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment