---
title: Legion Coder 8M - 10k Edition
emoji: 🚀
colorFrom: purple
colorTo: indigo
sdk: streamlit
sdk_version: "1.28.0"
python_version: "3.10"
app_file: app.py
pinned: false
---

# Legion Coder 8M - Dual Deploy Package

## Quick Deploy Options

### Option 1: Streamlit (Hugging Face Spaces)
```bash
# Install dependencies
pip install -r requirements_streamlit.txt

# Run locally
streamlit run app.py
```

**Deploy to Hugging Face Spaces:**
1. Go to https://huggingface.co/new-space
2. Select "Streamlit" as SDK
3. Upload `app.py` and `requirements_streamlit.txt`
4. Set model environment variable (optional)

### Option 2: Gradio (Local/Cloud)
```bash
# Install dependencies
pip install -r requirements_gradio.txt

# Run locally
python gradio_app.py
```

**Deploy to Hugging Face Spaces:**
1. Go to https://huggingface.co/new-space
2. Select "Gradio" as SDK
3. Upload `gradio_app.py` and `requirements_gradio.txt`

### Option 3: AWS SageMaker
```python
import sagemaker
from sagemaker.huggingface import HuggingFaceModel

huggingface_model = HuggingFaceModel(
model_data="pnny13/legion-coder-8m",
transformers_version="4.36.0",
pytorch_version="2.1.0",
py_version="py310",
role="YOUR_SAGEMAKER_ROLE",
)

predictor = huggingface_model.deploy(
initial_instance_count=1,
instance_type="ml.m5.large",
endpoint_name="legion-coder-8m"
)
```

## Model Information
- **Model ID**: dineth554/legion-coder-8m-10k
- **Parameters**: 44,341,632 (~44M)
- **Size**: ~170 MB
- **Format**: Safetensors
- **Context**: 1,024 tokens

## System Requirements
- CPU: 2+ cores
- RAM: 8GB minimum
- Python: 3.8+
- PyTorch: 2.0+

## Branding
- MADE WITH BY DEATH LEGION
- POWERED BY nvdya-kit
- 2026 Edition