PrototypeCommon
hkproj/rlhf-ppo
Notes and commented code for RLHF (PPO)
- Owner
- hkproj (personal account)
- Stars
- Stars: 139
- Forks
- Forks: 38
- Language
- Python
- License
- None
- Created
- 2024
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by hkproj
All 13 repos by hkproj- hkproj/pytorch-transformerStars: 1,329Jupyter NotebookBeta
- hkproj/pytorch-stable-diffusionStars: 1,086Jupyter NotebookBeta
- hkproj/pytorch-paligemmaStars: 638PythonAlpha
- hkproj/100-days-of-gpuStars: 452Alpha
- hkproj/transformer-from-scratch-notesStars: 395Alpha
- hkproj/pytorch-llamaStars: 382PythonAlpha
Nearby in Python
All Python repos- apimart-22w/gpt-5.5-apiStars: 139PythonPrototype
- cedardb/sqldoomStars: 139PythonPrototype
- DNFDEVS/medeo-fontStars: 139PythonPrototype
- brunobord/tdaemonStars: 139PythonPrototype
- internetarchive/bookserverStars: 139PythonPrototype
- caffeinehit/django-followStars: 139PythonPrototype