gpt-oss-20b thegovind · COMPLETED
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.
github.com/thegovind/gpt-oss-20b · ★ 0 · Forks 0 · Size 517 KB
SUMMARY
Technologies 2
Scored 2
Observed 2
Practices 6
Evidence 2
Skips 0
COVERAGE
Analyzed 6 files · 80 commits · 0 API calls
TECHNOLOGIES & DEPTH
Markdown LANGUAGE Depth 70
1 files · PRODUCTION
Python LANGUAGE Depth 70
3 files · PRODUCTION
PRACTICES
documentation · observedautomated_tests · absentcontinuous_integration · absentcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2025-10-04
Last commit 2025-12-02
Active months 3
Commits 80