lit-gpt Anindyadeep · COMPLETED
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
github.com/Anindyadeep/lit-gpt · ★ 0 · Forks 2 · Size 1.5 MB
SUMMARY
Technologies 10
Scored 10
Observed 10
Practices 6
Evidence 11
Skips 0
COVERAGE
Analyzed 115 files · 673 commits · 0 API calls
TECHNOLOGIES & DEPTH
Shell LANGUAGE Depth 70
1 files · PRODUCTION
Markdown LANGUAGE Depth 70
30 files · PRODUCTION
YAML LANGUAGE Depth 70
2 files · PRODUCTION
Python LANGUAGE Depth 70
71 files · PRODUCTION
pip BUILD_TOOL Depth 80
1 files · CONFIGURATION
NumPy LIBRARY Depth 85
6 files · PRODUCTION, TEST
Requests LIBRARY Depth 78
5 files · PRODUCTION, TEST
TypeScript LANGUAGE Depth 58
1 files · PRODUCTION
pandas LIBRARY Depth 58
1 files · PRODUCTION
pytest TESTING Depth 74
17 files · PRODUCTION, TEST
PRACTICES
documentation · observedautomated_tests · observedcontinuous_integration · observedcontainerization · absentlinting · absentformatting · absent
ACTIVITY & OWNERSHIP
First commit 2023-03-22
Last commit 2023-12-22
Active months 10
Commits 673