GSAI-ML

/

ESPO-Countdown

like 0

Follow

GSAI-ML 251

This PR significantly enhances the model card by:

• Adding pipeline_tag: text-generation to correctly classify the model's functionality and improve discoverability.
• Adding library_name: transformers to enable the automated "How to use" widget, as the model demonstrates compatibility with the transformers and peft libraries in its usage examples.
• Including direct links to the paper (Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective), the project page (https://jingyangou.github.io/ESPO-Demo/), and the GitHub repository (https://github.com/ML-GSAI/ESPO).
• Adding a "Sample Usage" section with a Python code snippet directly from the project's GitHub README, demonstrating how to load and use the LoRA adapter.
• Incorporating the paper's BibTeX citation for proper academic attribution.