hyunwoongko / nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.
Why this job: says: rlhf; topics: rlhf
What it does
This project aims to perform RLHF training from scratch, implementing almost all core components manually except for PyTorch and Triton. Each module is a minimal, educational reimplementation of large-scale systems focusing on clarity and core concepts rather than production readiness. This includes SFT and RL training pipeline with evaluation, for training a small Qwen3 model on open-source math datasets.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 9 months ago
- Stars
- 204
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v1.0.0
- Released 10 months ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 0 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| chi2liu / ABC-GRPO | 438 | 2 months ago | Apache-2.0 | No downloads |
| Enping-Hu / minimind-deep-dive | 217 | 22 days ago | CC-BY-4.0 | No downloads |
| adithya-s-k / FineEnvs | 560 | 15 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Shell 1%
Topics
- llm
- pytorch
- rlhf
- scratch-implementation
- triton
Project record
- JobFine-tuning
- StatusListed
- Commits334
- Forks18
- Watching2
- Stars in 28 days0
- CreatedSep 28, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026