README.md

---
title: Axon Llama GUI
emoji: 🧠
colorFrom: blue
colorTo: purple
sdk: docker
pinned: true
license: mit
short_description: Multimodal AI - Text, Images & Audio powered by Qwen2.5-Omni
---

# 🧠 Axon - Multimodal AI Assistant

A powerful multimodal AI assistant powered by **Qwen2.5-Omni-7B** running on llama.cpp. Handles text, images, and audio all in one model!

## ✨ Features

| Modality | Supported | Examples |
|----------|-----------|----------|
| 💬 Text | ✅ | Chat, Q&A, writing, reasoning, math |
| 🖼️ Images | ✅ | Describe images, read text, analyze charts |
| 🎵 Audio | ✅ | Transcribe speech, analyze audio content |

## 🔧 Technical Details

- **Model:** [Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)
- **Quantization:** Q8_0 (near-lossless quality)
- **Backend:** [llama.cpp](https://github.com/ggml-org/llama.cpp)
- **API:** OpenAI-compatible endpoints

## 🚀 API Usage

The server exposes OpenAI-compatible endpoints:
```bash
# Text chat
curl http://localhost:7860/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen2.5-omni-7b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
```

## 📝 Endpoints

| Endpoint | Description |
|----------|-------------|
| `/` | Web UI (llama.cpp chat interface) |
| `/v1/chat/completions` | OpenAI-compatible chat API |
| `/v1/models` | List available models |
| `/health` | Health check |

## 🙏 Credits

- [Qwen Team](https://github.com/QwenLM) for Qwen2.5-Omni
- [ggml-org](https://github.com/ggml-org) for llama.cpp
- [Hugging Face](https://huggingface.co) for hosting

## 📄 License

MIT License - See [LICENSE](LICENSE) for details.

---

<p align="center">
  Made with ❤️ by <a href="https://huggingface.co/Alencoder">Alencoder</a>
</p>