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.
Jupyter NotebookMIT
Issues
- 0
bug report
#10 opened by loadingyy - 0
bug report
#9 opened by loadingyy - 1
tokenizer.model?
#8 opened by loadingyy - 1
how to do the inference?
#7 opened by chowkamlee81 - 0
- 1
how to run InstructLLaMA on cpu
#5 opened by superclocks - 0
how to
#4 opened by superclocks - 0
https://github.com/Metaresearch/llama
#3 opened by superclocks