michaelnny / InstructLLaMA

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.
48Updated last year

Alternatives and similar repositories for InstructLLaMA:

Users that are interested in InstructLLaMA are comparing it to the libraries listed below