teilomillet/retrain
a Python library that uses Reinforcement Learning (RL) to train LLMs.
This tool helps AI researchers and machine learning engineers fine-tune large language models (LLMs) using reinforcement learning. You provide a configuration file detailing your model, training parameters, and reward setup, and it produces an optimized LLM adapter. It's designed for practitioners who need to run, compare, and reproduce various LLM training experiments efficiently.
Use this if you are an AI researcher or machine learning engineer looking to experiment with different reinforcement learning algorithms and reward functions to improve the performance of your LLMs.
Not ideal if you are a non-technical user seeking a no-code solution for basic LLM customization or if you prefer a graphical user interface for model training.
Stars
42
Forks
1
Language
Python
License
—
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/teilomillet/retrain"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scaleapi/llm-engine
Scale LLM Engine public repository
AGI-Arena/MARS
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
modelscope/easydistill
a toolkit on knowledge distillation for large language models
AGI-Edgerunners/LLM-Adapters
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient...
Wang-ML-Lab/bayesian-peft
Bayesian Low-Rank Adaptation of LLMs: BLoB [NeurIPS 2024] and TFB [NeurIPS 2025]