RL4LMs
Public一个模块化的强化学习库,用于根据人类偏好微调语言模型
dialogue-generationlanguage-modelingmachine-translationnatural-language-processingnlpreinforcement-learningsummarizationtable-to-texttext-generation
创建时间:2022-08-18T13:29:16
更新时间:2025-12-09T10:10:42
https://rl4lms.apps.allenai.org/
2.4K
Stars
2
Stars Increase