Hugging Face's logo

glab-caltech
/
TWIN-Qwen2.5-VL-3B

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_5_vl
visual-reasoning
fine-grained-vqa
fine-grained-recognition
conversational
text-generation-inference
Model card Files
xet
 Community
1

Add pipeline tag, library name, and dataset metadata

#1
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+12
-7
nielsr

This PR improves the model card by:

  • Adding pipeline_tag: image-text-to-text for better discoverability of this Vision-Language Model.
  • Adding library_name: transformers to indicate compatibility and enable the automated code snippet widget.
  • Linking the glab-caltech/TWIN dataset in the metadata.
  • Refining the metadata structure.
 Add pipeline tag, library name, and dataset metadata5219ac2a
dmarsili changed pull request status to merged

Sign up or log in to comment