4bit-fine-tune

There are 1 repositories under 4bit-fine-tune topic.

  • 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.

    Language:Jupyter Notebook47089