Instructions to use Qwen/Qwen-Audio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen-Audio with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/Qwen-Audio", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-Audio", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Qwen/Qwen-Audio with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen-Audio" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-Audio", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/Qwen-Audio
- SGLang
How to use Qwen/Qwen-Audio with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Qwen/Qwen-Audio" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-Audio", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Qwen/Qwen-Audio" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/Qwen-Audio", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/Qwen-Audio with Docker Model Runner:
docker model run hf.co/Qwen/Qwen-Audio
Update README.md
Browse files
README.md
CHANGED
|
@@ -20,7 +20,7 @@ inference: false
|
|
| 20 |
<p align="center">
|
| 21 |
Qwen-Audio <a href="https://www.modelscope.cn/models/qwen/QWen-Audio/summary">🤖 <a> | <a href="https://huggingface.co/Qwen/Qwen-Audio">🤗</a>  | Qwen-Audio-Chat <a href="https://www.modelscope.cn/models/qwen/QWen-Audio-Chat/summary">🤖 <a>| <a href="https://huggingface.co/Qwen/Qwen-Audio-Chat">🤗</a>  |    Demo<a href="https://modelscope.cn/studios/qwen/Qwen-Audio-Chat-Demo/summary"> 🤖</a> | <a href="https://huggingface.co/spaces/Qwen/Qwen-Audio">🤗</a> 
|
| 22 |
<br>
|
| 23 |
-
  <a href="https://qwen-audio.github.io/Qwen-Audio/">Homepage</a>  |  <a href="http://arxiv.org/abs/2311.07919">Paper</a>
|
| 24 |
</p>
|
| 25 |
<br><br>
|
| 26 |
|
|
|
|
| 20 |
<p align="center">
|
| 21 |
Qwen-Audio <a href="https://www.modelscope.cn/models/qwen/QWen-Audio/summary">🤖 <a> | <a href="https://huggingface.co/Qwen/Qwen-Audio">🤗</a>  | Qwen-Audio-Chat <a href="https://www.modelscope.cn/models/qwen/QWen-Audio-Chat/summary">🤖 <a>| <a href="https://huggingface.co/Qwen/Qwen-Audio-Chat">🤗</a>  |    Demo<a href="https://modelscope.cn/studios/qwen/Qwen-Audio-Chat-Demo/summary"> 🤖</a> | <a href="https://huggingface.co/spaces/Qwen/Qwen-Audio">🤗</a> 
|
| 22 |
<br>
|
| 23 |
+
  <a href="https://qwen-audio.github.io/Qwen-Audio/">Homepage</a>  |  <a href="http://arxiv.org/abs/2311.07919">Paper</a> |  <a href="https://huggingface.co/papers/2311.07919">🤗</a>
|
| 24 |
</p>
|
| 25 |
<br><br>
|
| 26 |
|