PrototypeCommon
hyunwoongko/nanoRLHF
nanoRLHF: from-scratch journey into how LLMs and RLHF really work.
- Owner
- hyunwoongko (personal account)
- Stars
- Stars: 204
- Forks
- Forks: 19
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Topics
- llmpytorchrlhfscratch-implementationtriton
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by hyunwoongko
All 7 repos by hyunwoongko- hyunwoongko/transformerStars: 4,685PythonRC
- hyunwoongko/kssStars: 468PythonAlpha
- hyunwoongko/kochatStars: 460PythonAlpha
- hyunwoongko/openchatStars: 428PythonAlpha
- hyunwoongko/pecabStars: 172PythonPrototype
- hyunwoongko/solar-vs-glm-vs-phiStars: 100PythonPrototype
Nearby in Python
All Python repos- PINTO0309/High-Angle_Robust_Fast_FaceAlignmentStars: 204PythonPrototype
- ziangni-sys/claude-passnoteStars: 204PythonPrototype
- R238Company/meu-emprego-novoStars: 204PythonPrototype
- scrapinghub/python-scrapinghubStars: 204PythonPrototype
- hcientist/OnlinePythonTutorStars: 204PythonPrototype
- kivy/audiostreamStars: 204PythonPrototype