Popular repositories Loading

1. CORECODE CORECODE Public

   3

2. IRCAN IRCAN Public

   Python 3

3. UltraFeedback UltraFeedback Public

   Forked from OpenBMB/UltraFeedback

   A large-scale, fine-grained, diverse preference dataset (and models).

   Python

4. dpo_toxic dpo_toxic Public

   Forked from ajyl/dpo_toxic

   A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.

   Jupyter Notebook

5. trl trl Public

   Forked from huggingface/trl

   Train transformer language models with reinforcement learning.

   Python

6. direct-preference-optimization direct-preference-optimization Public

   Forked from eric-mitchell/direct-preference-optimization

   Reference implementation for DPO (Direct Preference Optimization)

   Python