PrototypeCommon
HamzaElshafie/gpt-oss-20B
A PyTorch implementation of the GPT-OSS-20B architecture. All components are coded from scratch: RoPE with YaRN, RMSNorm, SwiGLU with clamping and residual connection, Mixture-of-Experts (MoE), Self-Attention with learned sinks, banded attention, GQA, and KV-cache.
- Owner
- HamzaElshafie (personal account)
- Stars
- Stars: 238
- Forks
- Forks: 18
- Language
- Python
- License
- Apache-2.0
- Created
- 2025
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Python
All Python repos- APUS-AI-Lab/fast-browser-useStars: 238PythonPrototype
- RISE-X-Lab/SPROUTStars: 238PythonPrototype
- NoizAI/WorldSonusStars: 238PythonPrototype
- jazzband/django-mongonautStars: 238PythonPrototype
- charettes/django-mutantStars: 238PythonPrototype
- shackenberg/Minimal-Bag-of-Visual-Words-Image-ClassifierStars: 238PythonPrototype