yichengchen24

/

DataChef-32B

like 1

Hi! I'm Niels from the Hugging Face community science team. I noticed this model card was missing a description and links to relevant resources.

This PR:

• Adds a description of the model based on the paper DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning.
• Includes links to the official GitHub repository and the Hugging Face demo.
• Adds citation information for researchers.
• Updates the metadata to ensure consistency.