THUDM/slime slime 是一个旨在扩展强化学习(RL)的大型语言模型(LLM)后训练框架。 语言:Python Star 数:342 问题数:4 Fork 数:13 项目地址:https://github.com/THUDM/slime

----------------------

THUDM/slime
slime is a LLM post-training framework aiming at scaling RL.
Language: Python
Stars: 342 Issues: 4 Forks: 13
https://github.com/THUDM/slime
GitHub
GitHub - THUDM/slime: slime is a LLM post-training framework aiming at scaling RL.

slime is a LLM post-training framework aiming at scaling RL. - THUDM/slime


via GitHub repos - Telegram Channel
 
 
Back to Top
Copyright © 2025 BESTAI. All rights reserved.
BEST AI API中转 - OpenAI DeepSeek Claude Gemini Grok MidJourney 2.8折起
[email protected]