jackaduma / chatglm-lora-rlhf-pytorch Goto Github PK
View Code? Open in Web Editor NEWA full pipeline to finetune ChatGLM LLM with LoRA and RLHF on consumer hardware. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the ChatGLM architecture. Basically ChatGPT but with ChatGLM
License: MIT License