PersonalAILab

/

GRM-Qwen2.5-14B-Instruct

like 0

Follow

OPPO-Personal-AI-Lab 55

This PR adds a comprehensive model card for the Personalized-Qwen2.5-14B-Instruct model to the Hugging Face Hub.

The new model card includes:

• A link to the paper: Towards Faithful and Controllable Personalization via Critique-Post-Edit Reinforcement Learning.
• The appropriate license (Apache 2.0).
• The library_name (transformers), enabling the automated code snippet for usage on the Hugging Face Hub.
• The pipeline_tag (text-generation), making the model easily discoverable for relevant tasks.
• A link to the GitHub repository for more details and code.
• Key experimental results and acknowledgements from the original GitHub README.

A manual sample usage snippet is not included in the model card content, as no such snippet was provided in the original GitHub README. However, the library_name tag ensures that users will find an automated usage example on the model page.

Please review and merge this PR.