Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,12 +1,67 @@
|
|
| 1 |
---
|
| 2 |
title: Axon Llama GUI
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: docker
|
| 7 |
-
pinned:
|
| 8 |
license: mit
|
| 9 |
-
short_description:
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: Axon Llama GUI
|
| 3 |
+
emoji: 🧠
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: docker
|
| 7 |
+
pinned: true
|
| 8 |
license: mit
|
| 9 |
+
short_description: Multimodal AI - Text, Images & Audio powered by Qwen2.5-Omni
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# 🧠 Axon - Multimodal AI Assistant
|
| 13 |
+
|
| 14 |
+
A powerful multimodal AI assistant powered by **Qwen2.5-Omni-7B** running on llama.cpp. Handles text, images, and audio all in one model!
|
| 15 |
+
|
| 16 |
+
## ✨ Features
|
| 17 |
+
|
| 18 |
+
| Modality | Supported | Examples |
|
| 19 |
+
|----------|-----------|----------|
|
| 20 |
+
| 💬 Text | ✅ | Chat, Q&A, writing, reasoning, math |
|
| 21 |
+
| 🖼️ Images | ✅ | Describe images, read text, analyze charts |
|
| 22 |
+
| 🎵 Audio | ✅ | Transcribe speech, analyze audio content |
|
| 23 |
+
|
| 24 |
+
## 🔧 Technical Details
|
| 25 |
+
|
| 26 |
+
- **Model:** [Qwen2.5-Omni-7B](https://huggingface.co/Qwen/Qwen2.5-Omni-7B)
|
| 27 |
+
- **Quantization:** Q8_0 (near-lossless quality)
|
| 28 |
+
- **Backend:** [llama.cpp](https://github.com/ggml-org/llama.cpp)
|
| 29 |
+
- **API:** OpenAI-compatible endpoints
|
| 30 |
+
|
| 31 |
+
## 🚀 API Usage
|
| 32 |
+
|
| 33 |
+
The server exposes OpenAI-compatible endpoints:
|
| 34 |
+
```bash
|
| 35 |
+
# Text chat
|
| 36 |
+
curl http://localhost:7860/v1/chat/completions \
|
| 37 |
+
-H "Content-Type: application/json" \
|
| 38 |
+
-d '{
|
| 39 |
+
"model": "qwen2.5-omni-7b",
|
| 40 |
+
"messages": [{"role": "user", "content": "Hello!"}]
|
| 41 |
+
}'
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
## 📝 Endpoints
|
| 45 |
+
|
| 46 |
+
| Endpoint | Description |
|
| 47 |
+
|----------|-------------|
|
| 48 |
+
| `/` | Web UI (llama.cpp chat interface) |
|
| 49 |
+
| `/v1/chat/completions` | OpenAI-compatible chat API |
|
| 50 |
+
| `/v1/models` | List available models |
|
| 51 |
+
| `/health` | Health check |
|
| 52 |
+
|
| 53 |
+
## 🙏 Credits
|
| 54 |
+
|
| 55 |
+
- [Qwen Team](https://github.com/QwenLM) for Qwen2.5-Omni
|
| 56 |
+
- [ggml-org](https://github.com/ggml-org) for llama.cpp
|
| 57 |
+
- [Hugging Face](https://huggingface.co) for hosting
|
| 58 |
+
|
| 59 |
+
## 📄 License
|
| 60 |
+
|
| 61 |
+
MIT License - See [LICENSE](LICENSE) for details.
|
| 62 |
+
|
| 63 |
+
---
|
| 64 |
+
|
| 65 |
+
<p align="center">
|
| 66 |
+
Made with ❤️ by <a href="https://huggingface.co/Alencoder">Alencoder</a>
|
| 67 |
+
</p>
|