Repository · GitHub

jackaduma/ChatGLM-LoRA-RLHF-PyTorch

A 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

View on GitHubReport an issue

Owner	jackaduma
License (as declared)	MIT
Stars	138
Forks	9
Main language	Python
Created	18 April 2023
Last updated at source	28 April 2023

pythonchatglmchatglm-6bchatgptdeepspeedfinetunegptllamallmlorapeftppopytorchreward-modelsrlhf

Embed this entry

<iframe src="https://silytics.si/embed/item/5f68b43c-7507-4e84-a0c6-a573657732cd" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Stars, last 5 days

138 now. Counts as reported by the source, snapshotted daily by Silytics.

More from jackaduma

awesome_LLMs_interview_notesRepository
CycleGAN-VC2Repository
Vicuna-LoRA-RLHF-PyTorchRepository
SecBERTRepository
Recurrent-LLMRepository
CycleGAN-VC3Repository

Silytics shows public metadata from GitHub and links to the original. Information may be incomplete or out of date. Last refreshed 20 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.