AIbase

InstructLLaMA

Public

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 InstructGPT or ChatGPT, but on a much smaller scale.

Creat2023-07-08T21:58:22
Update2025-02-02T09:06:07
51
Stars
0
Stars Increase

Related projects