Pinned Loading

1. async_rlhf async_rlhf Public

   Code and Configs for Asynchronous RLHF: Faster and More Efficient RL for Language Models

   Python 19 1

2. elastic-reset elastic-reset Public

   Code and Experiments for "Language Model Alignment with Elastic Reset" (NeurIPS 2023)

   Python 5

3. vwxyzjn/summarize_from_feedback_details vwxyzjn/summarize_from_feedback_details Public

   Python 120 16

4. emergent-compete emergent-compete Public

   Code for Emergent Communication under Competition (AAMAS 2021)

   Jupyter Notebook 10 1

5. huggingface/trl huggingface/trl Public

   Train transformer language models with reinforcement learning.

   Python 10.4k 1.3k

6. lecture-notes lecture-notes Public

   LaTeX lecture notes CS/ML courses at University of Waterloo and Universite de Montreal

   TeX 10 8