Definition
Hugging Face's library for reinforcement-learning post-training of language models.
Transformer Reinforcement Learning, an open-source library for SFT, RLHF, and DPO-style post-training of language models.
Hugging Face's library for reinforcement-learning post-training of language models.
Transformer Reinforcement Learning, an open-source library for SFT, RLHF, and DPO-style post-training of language models.