A lightweight Transformer training & inference framework
## 📖 Table of Contents
English
- [Features](#features)
- [Quick Start](#quick-start)
- [Documentation](#documentation)
- [Contributing](#contributing)
- [Community](#community)
- [License](#license)
---
## English
### Features
- 🚀 **High Performance**: Optimized for both training and inference with efficient parallelization.
- 🔧 **Flexible**: Support for seq/sft/dpo/grpo training, customizable model architectures.
- 💡 **Easy to Use**: Simple API with comprehensive examples and demos.
- 📦 **Lightweight**: Minimal dependencies, easy to deploy.
- 🔬 **Research‑Friendly**: Modular design, easy to experiment with new ideas.
- 🤗 **HuggingFace Integration**: Compatible with HuggingFace models and datasets.
### Quick Start
#### Installation
```bash
git clone https://github.com/ViperEkura/AstrAI.git
cd AstrAI
pip install -e .
```
For development dependencies:
```bash
pip install -e ".[dev]"
```
#### Train a Model
```bash
python scripts/tools/train.py \
--train_type=seq \
--data_root_path=/path/to/dataset \
--param_path=/path/to/param_path
```
#### Generate Text
```bash
python scripts/tools/generate.py --param_path=/path/to/param_path
```
#### Docker
Build and run with Docker (recommended for GPU environments):
```bash
# Build image
docker build -t astrai:latest .
# Run with GPU support
docker run --gpus all -it astrai:latest
# Run with specific GPUs
docker run --gpus '"device=0,1"' -it astrai:latest
# Run inference server
docker run --gpus all -p 8000:8000 astrai:latest \
python -m scripts.tools.server --port 8000 --device cuda
# Run with volume mount for data
docker run --gpus all -v /path/to/data:/data -it astrai:latest
```
> **Note**: `--gpus all` is required for CUDA support. Without it, `torch.cuda.is_available()` will return `False`.
#### Start HTTP Server
Start the inference server with OpenAI-compatible HTTP API:
```bash
python -m scripts.tools.server --port 8000 --device cuda
```
Make requests:
```bash
# Chat API (OpenAI compatible)
curl -X POST http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 512
}'
# Streaming response
curl -X POST http://localhost:8000/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"messages": [{"role": "user", "content": "Tell a story"}],
"stream": true,
"max_tokens": 500
}'
# Health check
curl http://localhost:8000/health
```
#### Demo
Check out the demos in the `scripts/demo/` folder:
```bash
# Download pre‑processed data (required before running demos)
python scripts/demo/download.py
# Interactive streaming chat
python scripts/demo/stream_chat.py
# Batch generation
python scripts/demo/generate_batch.py
# Auto‑regressive generation
python scripts/demo/generate_ar.py
```
Watch a video walkthrough on [bilibili](https://www.bilibili.com/video/BV1z5RPYHEkd).
### Documentation
| Document | Description |
|----------|-------------|
| [Parameter Guide](./assets/docs/params.md) | Training & inference parameters |
| [Design Document](./assets/docs/design.md) | Framework architecture & module design |
| [Data Flow](./assets/docs/dataflow.md) | Data processing pipeline details |
| [Model Introduction](./assets/docs/introduction.md) | Model architecture & technical details |
### Contributing
We welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details.
1. Fork the repository.
2. Create a feature branch.
3. Commit your changes.
4. Open a Pull Request.
For major changes, please open an issue first to discuss what you would like to change.
### Community
- **GitHub Issues**: [Issue Tracker](https://github.com/ViperEkura/AstrAI/issues)
- **Discussions**: [GitHub Discussions](https://github.com/ViperEkura/AstrAI/discussions)
- **HuggingFace**: [Model Hub](https://huggingface.co/ViperEk)
### License
This project is licensed under the [GPL-3.0 License](LICENSE).
---
A lightweight Transformer framework designed for both high performance and ease of use.
