1 result found Sort:

michaelnny
InstructLLaMA michaelnny
9
33
mit
0
Implements pre-training, supervised fine-tuning (SFT), and reinforcement learning from human feedback (RLHF), to train and fine-tune the LLaMA2 model to follow human instructions, similar to InstructG...
ppo rhlf llam2 qlora instructgpt 4bit-fine-tune
Created 2023-07-08
35 commits to main branch, last one 3 months ago