dipta007

/

question-judge-balanced

like 0

Hi! I'm Niels from the community science team at Hugging Face. This PR improves the model card for the DecomposeRL Tiny Judge classifier.

Specifically, I have:

• Added the text-classification pipeline tag and transformers library name.
• Included metadata for the base model (ModernBERT-large) and the associated dataset.
• Linked the model to the original paper, GitHub repository, and project page.
• Provided a description of the model's function as a distilled reward judge for claim verification.