Jingbiao

/

Qwen2-VL-7B-Harm-C-LMM-RGCL

like 0

This PR significantly improves the model card for the model presented in Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detection.

Key changes include:

• Updated library_name to transformers: This ensures the "How to use" widget properly displays a transformers code snippet, as the model is compatible with transformers for loading and inference of its PEFT adapters.
• Added pipeline_tag: image-text-to-text: This makes the model discoverable under the appropriate task category on the Hugging Face Hub, reflecting its multimodal input and text output capabilities.
• Added license: cc-by-4.0: Provides clear licensing information.
• Added language: en and relevant tags: Enhances model discoverability.
• Populated model card content: The model card now includes the paper title, Hugging Face paper link, the abstract as a detailed model description, and filled-out sections for model details, uses, biases, training, and evaluation, providing comprehensive information about the model.
• Added BibTeX citations: The provided BibTeX entries for the associated papers are now correctly placed in the "Citation" section.

Please review and merge this PR if everything looks good.