Pinned Loading

1. ContextualAI/HALOs ContextualAI/HALOs Public

   A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

   Python 740 45

2. dataset_difficulty dataset_difficulty Public

   "Understanding Dataset Difficulty with V-Usable Information" (ICML 2022, outstanding paper)

   Jupyter Notebook 82 13

3. huggingface/trl huggingface/trl Public

   Train transformer language models with reinforcement learning.

   Python 10.1k 1.3k