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

36
/ 100
Emerging

This project provides a complete process for customizing a ChatGLM language model to better suit your specific needs, even if you only have common computer hardware. You feed in your own dataset, and the system outputs a fine-tuned ChatGLM model that is more aligned with your instructions and preferences. This is for AI researchers or data scientists who want to create specialized conversational AI.

140 stars. No commits in the last 6 months.

Use this if you need to adapt a powerful large language model like ChatGLM for a niche application or specific style of interaction on consumer-grade GPUs.

Not ideal if you're looking for a pre-trained, ready-to-use chatbot or if you don't have the technical expertise to manage model training workflows.

custom-LLM-development conversational-AI-specialization NLP-model-adaptation AI-research natural-language-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

140

Forks

9

Language

Python

License

MIT

Last pushed

Apr 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.