Metadata-Version: 2.4
Name: onyx-AI-Qwen2
Version: 0.1.1
Summary: Professional Streaming Engine for Qwen2 models by ONYX
Author-email: Rawan Jassim <eng.rawan.abd.alrazak@gmail.com>
Project-URL: Homepage, https://github.com/RUI-com/
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Requires-Dist: fastapi
Requires-Dist: uvicorn
Requires-Dist: transformers>=4.48.0
Requires-Dist: torch
Requires-Dist: accelerate
Requires-Dist: einops
Requires-Dist: sentencepiece
Requires-Dist: protobuf
Requires-Dist: tiktoken

<p align="center">
  <img src="https://onyxchat-ai.vercel.app/logo/Group%2071.png" alt="ONYX AI Logo" width="200">
</p>

# 💎 ONYX AI Qwen2 Engine

High-performance streaming server for Qwen2 models, optimized for **ONYX** platform.

## 📦 Installation
```bash
pip install onyx-AI-Qwen2
```
Option 2: requirements.txt
```txt
fastapi
uvicorn
transformers>=4.48.0
torch
accelerate
einops
sentencepiece
protobuf
tiktoken
onyx-AI-Qwen2
```
---
💻 Usage
▶ Standard Script
```python
from ONYXAI_Qwen2 import OnyxQwenEngine

# 1. إنشاء المحرك
engine = OnyxQwenEngine(model_id="Qwen/Qwen2.5-1.5B-Instruct")

# 2. استخراج الـ app 
app = engine.app 

if __name__ == "__main__":
    engine.run(port=7860)
```
---
🛠 API Usage
Endpoint
```
POST /predict
```
Example Request
```json
{
  "messages": [
    {
      "role": "user",
      "content": "Write a long story about space exploration."
    }
  ],
  "stream": true,
  "temperature": 0.7,
  "max_tokens": 1024
}
```
---
🔗 Links
Organization: [ONYX / RUI Company](https://github.com/RUI-com/)
Author: [Eng. Rawan Jassim](https://eng-rawan-abd-alrazak-next-js-website-main.vercel.app/)
---
© 2026 ONYX. All rights reserved.
