Wnn

C 62 completed
Ai Ml
web_app / python · small
373
Files
101,786
LOC
5
Frameworks
13
Languages

Pipeline State

completed
Run ID
#353567
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Cataloged
Decision
proceed
Novelty
77.67
Framework unique
Isolation
Last stage change
2026-05-10 03:35:31
Deduplication group #55950
Member of a group with 1 similar repo(s) — this repo is canonical view group →
Top concepts (2)
Project DescriptionWeb Frontend
Same scanner, your repo: https://repobility.com — Repobility

AI Prompt

Create a Python-based language modeling project that implements Weightless Neural Networks (WNNs) using a RAM-based approach within PyTorch. The core functionality should involve training a model, like the BitwiseRAMLM, on text data, such as WikiText-2. I need to see the structure for loading tokens, training the model using a specified number of tokens, and evaluating the results to get metrics like Cross-Entropy and Perplexity. Please ensure the setup is robust enough for research use.
python pytorch language-modeling nn pytorch research web-app
Generated by gemma4:latest

Catalog Information

This project implements Weightless Neural Networks for language modeling using a RAM-based approach in the PyTorch framework.

Description

The ram-wnn project utilizes Weightless Neural Networks to perform language modeling tasks. It leverages a RAM-based architecture, which is implemented using the PyTorch library. This approach enables efficient and effective processing of linguistic data. The project's primary focus is on developing a novel neural network design for natural language processing applications.

الوصف

يستخدم مشروع ram-wnn شبكات عصبية خفيفة للتعلم اللغوي باستخدام نهج ذاكرة RAM. يتم تنفيذ هذه الشبكة باستخدام مكتبة PyTorch. يتيح هذا النهج معالجة كفاءة ومؤثفة للبيانات اللغوية. تركز المشروع على تطوير تصميم شبكة عصبية جديد للوظائف التعلم اللغوي.

Novelty

7/10

Tags

language-modeling natural-language-processing neural-networks weightless-neural-networks ram-based-architecture

Technologies

huggingface pytorch

Claude Models

claude-opus-4.6

Quality Score

C
61.5/100
Structure
72
Code Quality
52
Documentation
77
Testing
65
Practices
47
Security
55
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Code linting configured (ruff (possible))
  • Properly licensed project

Weaknesses

  • 1 files with critical complexity need refactoring
  • 1 bare except/catch blocks swallowing errors
  • 20453 duplicate lines detected \u2014 consider DRY refactoring
  • 41 'god files' with >500 LOC need decomposition

Recommendations

  • Replace bare except/catch blocks with specific exception types
  • Address 22 TODO/FIXME items \u2014 consider tracking them as issues

Security & Health

27.1h
Tech Debt (A)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (1)
Repobility · open methodology · https://repobility.com/research/
MIT
License
14.3%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
56.3%
rust
25.6%
svelte
5.7%
swift
4.8%
markdown
3.7%
json
2.2%
typescript
0.8%
shell
0.5%
css
0.1%
yaml
0.1%
toml
0.1%
javascript
0.0%

Frameworks

Svelte SvelteKit Axum pytest Vite

Concepts (2)

Analysis by Repobility (https://repobility.com) · MCP-ready
CategoryNameDescriptionConfidence
Repobility — same analyzer, your code, free for public repos · /scan/
auto_descriptionProject DescriptionWeightless Neural Networks for Language Modeling — RAM-based neurons in PyTorch.80%
auto_categoryWeb Frontendweb-frontend70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/77681.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV