safe-rlhf

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.