The Fine-Tuning Index / RLHF & Preference / #116
zht8506/Easy-LLM-Post-Training
by zht8506 · RLHF & Preference · updated 4mo ago
Implement popular LLM post-training algorithms (SFT, DFT, DPO, GRPO, etc.) in PyTorch with easy code!
31
momentum
113
stars
10
forks
#116
rank