2218342221/llm-post-training-book
Bilingual graduate textbook on LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, reasoning, agents, systems, evaluation, and safety.
正在读取项目信息…
开源雷达国内 GitHub 镜像站
加速通道已就绪
返回列表
开源雷达国内 GitHub 镜像站
Bilingual graduate textbook on LLM post-training: SFT, RLHF, DPO, GRPO, RLVR, reasoning, agents, systems, evaluation, and safety.