A hub that integrates a variety of effective algorithms to optimize the "Llama-2" model, focusing on the RLHF of the "Llama-2" model.
DengYangyong/LlamaRLHFHub
A hub that integrates a variety of effective algorithms to optimize the "Llama-2" model, focusing on the RLHF of the "Llama-2" model.
Python