none0663/slime
slime is a LLM post-training framework for RL Scaling.
Repositories
none0663/openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
none0663/none0663
Config files for my GitHub profile.
none0663/verl
veRL: Volcano Engine Reinforcement Learning for LLM
none0663/mbridge
Bridge Megatron-Core to Hugging Face/Reinforcement Learning
none0663/Megatron-LM
Ongoing research training transformer models at scale
none0663/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
none0663/PARL
A high-performance distributed training framework for Reinforcement Learning