sunzeyeah/RLHF
Implementation of Chinese ChatGPT
This project provides a comprehensive toolkit for building and refining Chinese-language conversational AI models similar to ChatGPT. It helps you take a base language model, fine-tune it with specific Chinese data, and then further enhance its conversational abilities based on human feedback. The output is a high-performing Chinese ChatGPT-like model, and it's ideal for AI engineers or researchers focused on developing advanced Chinese NLP applications.
289 stars. No commits in the last 6 months.
Use this if you need to train or evaluate large language models, specifically focusing on building a Chinese-language ChatGPT-style assistant, leveraging methods like Supervised Fine-Tuning (SFT), Reward Modeling, and Reinforcement Learning from Human Feedback (RLHF) or DPO.
Not ideal if your focus is on non-Chinese languages, or if you are looking for a pre-built, off-the-shelf chatbot without the need for custom training or model evaluation.
Stars
289
Forks
35
Language
Python
License
—
Category
Last pushed
Nov 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/sunzeyeah/RLHF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
openai/openai-cookbook
Examples and guides for using the OpenAI API
rgbkrk/dangermode
Execute IPython & Jupyter from the comforts of chat.openai.com
CogStack/OpenGPT
A framework for creating grounded instruction based datasets and training conversational domain...
Declipsonator/GPTZzzs
Large language model detection evasion through grammar and vocabulary modifcation.
flypythoncom/python
python is all you need !