Hugging Face's logo

tencent
/
Youtu-Parsing

Image-Text-to-Text
Transformers
Safetensors
youtu_vl
text-generation
conversational
custom_code
Model card Files
xet
Community
2

Improve model card: add transformers library, pipeline tag, and paper link

#2
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+76
-35
nielsr

This PR improves the model card for Youtu-Parsing by:

  1. Adding the library_name: transformers tag to metadata, as the model configuration supports the transformers auto-mapping.
  2. Updating the pipeline_tag to image-segmentation to reflect the vision-centric capabilities described in the associated paper.
  3. Linking the model card to the corresponding Hugging Face paper page: Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision.
  4. Adding a "Sample Usage" section with a code snippet from the official GitHub README to demonstrate how to use the model with the transformers library.
 Improve model card: add transformers library, pipeline tag, and paper linkc3b2c7c4
Yinsongliu
 Tencent org

Thanks for your feedback. This model requires an SDK for usage, and it cannot yet achieve the intended performance when used directly with Transformers. We will adopt the modification to set library_name: transformers and update it as soon as possible.

Yinsongliu changed pull request status to closed

Sign up or log in to comment