The Fine-Tuning Index / RLHF & Preference / #91
zht8506/Easy-LLM-Post-Training
by zht8506 · RLHF & Preference · updated 3mo ago
Implement popular LLM post-training algorithms (SFT, DFT, DPO, GRPO, etc.) in PyTorch with easy code!
39
momentum
116
stars
10
forks
#91
rank