li-plus/nanoRLHF
Train a tiny LLaMA model from scratch to repeat your words using Reinforcement Learning from Human Feedback (RLHF)
This tool allows developers to experiment with training a small language model to precisely echo input text. By providing a list of words, you can train a model from scratch to accurately repeat what it's given, demonstrating the Reinforcement Learning from Human Feedback (RLHF) process. It's designed for machine learning engineers and researchers looking to understand or prototype RLHF techniques.
No commits in the last 6 months.
Use this if you are a machine learning practitioner interested in a hands-on, simplified demonstration of how to train a language model using the PPO algorithm within an RLHF framework.
Not ideal if you need a production-ready large language model or a tool for general natural language processing tasks beyond simple repetition.
Stars
18
Forks
1
Language
Python
License
MIT
Category
Last pushed
May 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/li-plus/nanoRLHF"
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.