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
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.
Stars
140
Forks
9
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
agentscope-ai/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement...
OpenRLHF/OpenRLHF
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO &...
zjunlp/EasyEdit
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.
huggingface/alignment-handbook
Robust recipes to align language models with human and AI preferences
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.