Nornmuoncautiouswd
D 51 completed
Other
library / python · tiny
4
Files
426
LOC
0
Frameworks
2
Languages
Pipeline State
completedRun ID
#1532666Phase
doneProgress
0%Started
2026-04-16 14:50:36Finished
2026-04-16 14:50:36LLM tokens
0Pipeline Metadata
Stage
SkippedDecision
skip_tinyNovelty
17.45Framework unique
—Isolation
—Last stage change
2026-04-16 18:15:42Deduplication group #47371
Member of a group with 311 similar repo(s) — canonical #1523155 view group →
Repobility · code-quality intelligence platform · https://repobility.com
🧪 Code Distillation
Browse all specs →AI Prompt
Create a Python library implementation for the NorMuon optimization algorithm, based on the concepts from the NorMuon paper. The library should be structured so that users can easily install it via pip. It needs to handle various recommended parameters like `lr`, `momentum`, `beta2`, and `weight_decay`. Please include usage examples demonstrating how to apply the optimizer, especially showing the recommended way to route parameters for single-device training using `SingleDeviceNorMuon` or `SingleDeviceNorMuonWithAuxAdam`.
python library optimization machine-learning pytorch deep-learning algorithm
Generated by gemma4:latest
Catalog Information
Create a Python library implementation for the NorMuon optimization algorithm, based on the concepts from the NorMuon paper. The library should be structured so that users can easily install it via pip. It needs to handle various recommended parameters like lr, momentum, beta2, and weight_decay. Please include usage examples demonstrating how to apply the optimizer, especially showing the recommended way to route parameters for single-device training using SingleDeviceNorMuon or `Singl
Tags
python library optimization machine-learning pytorch deep-learning algorithm
Quality Score
D
51.0/100
Structure
45
Code Quality
45
Documentation
60
Testing
0
Practices
78
Security
100
Dependencies
80
Strengths
- Consistent naming conventions (snake_case)
- Good security practices — no major issues detected
- Properly licensed project
Weaknesses
- No tests found — high risk of regressions
- No CI/CD configuration — manual testing and deployment
- 165 duplicate lines detected — consider DRY refactoring
Recommendations
- Add a test suite — start with critical path integration tests
- Set up CI/CD (GitHub Actions recommended) to automate testing and deployment
- Add a linter configuration to enforce code style consistency
Languages
Frameworks
None detected
Symbols
function11
method8
class4
constant2
Embed Badge
Add to your README:
Repobility · code-quality intelligence · https://repobility.com
BinComp Dependency Hardening
All packages →2 of this repo's dependencies have been scanned for binary hardening. Grade reflects RELRO / stack canary / FORTIFY / PIE coverage.