ContextualAI/HALOs · AI Repo StatsCOContextualAI/HALOs
A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).
Training & fine-tuningPython Apache-2.0 50created 2023-12-03 #alignment#dpo#halos#kto#ppo#rlhf