Spaces:
Sleeping
Sleeping
metadata
title: Legion Coder
emoji: ⚡
colorFrom: red
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
license: mit
⚡ Legion Coder
A 44M Parameter Transformer for Code Generation
🚀 About
Legion Coder is a compact yet powerful 44M parameter transformer model optimized for coding tasks. Built with precision by DEATH LEGION and powered by nvdya-kit, this model delivers high-quality code generation in a lightweight package.
✨ Features
- 📝 Clean Code Generation - PEP 8 compliant Python and more
- 🐛 Debug Assistance - Help identify and fix code issues
- 📚 Code Explanation - Understand complex programming concepts
- 💡 Multi-language Support - Python, JavaScript, and more
- ⚡ Fast Inference - Optimized for CPU deployment
📊 Model Specifications
| Attribute | Value |
|---|---|
| Parameters | 44,341,632 (~44M) |
| Architecture | GPT-style Transformer |
| Hidden Size | 576 |
| Layers | 13 |
| Attention Heads | 16 |
| Context Length | 1,024 tokens |
| Vocabulary | 16,000 tokens |
| Format | Safetensors |
🎯 Use Cases
- Code Completion - Finish partial code snippets
- Function Generation - Create functions from descriptions
- Debugging - Find and fix errors in code
- Learning - Get explanations for programming concepts
- Prototyping - Quickly generate code scaffolding
🛠️ Technical Details
Training Data
- Python code from The Stack v2 dataset
- GitHub code repositories (filtered for quality)
- Code-specific preprocessing for indentation and special tokens
Training Procedure
- Optimizer: AdamW
- Learning Rate: 5e-4 with cosine decay
- Batch Size: 4 with gradient accumulation
- Training Steps: 10,000
- Precision: float32 (CPU-optimized)
📝 License
This model is released under the MIT License.
🔗 Links
- Model Repository: dineth554/legion-coder-8m
- Space: This Space