by teilomillet · MCP Server · ★ 43
retrain is a TOML-first RLVR (Reinforcement Learning with Verifiable Rewards) trainer for LLMs, built to make experiments easier to run, compare, and repeat. If you are new, start with install - explore commands - run a tiny config. Install Requires Python 3.11+. If you are developing this repo directly: Explore the CLI Use these first to understand what exists before you train: Useful inspection commands while iterating: Tiny TOML Demo Create : below is an intentional smoke-test profile. The standard default for full runs is .
| Stars | 43 |
| Forks | 2 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 67.7352227417039/100 |
| Open Issues | 2 |
| Last Updated | 2026-07-06 |
| Created | 2025-04-03 |
| Platforms | mcp, python |
| Est. Tokens | ~14k |
Explore other popular mcp server tools:
retrain is a Python library that uses Reinforcement Learning (RL) to train LLMs.. It is categorized as a MCP Server with 43 GitHub stars.
retrain is primarily written in Python. It covers topics such as deepseek, llm, mcp.
You can find installation instructions and usage details in the retrain GitHub repository at github.com/teilomillet/retrain. The project has 43 stars and 2 forks, indicating an active community.