Instructions to use Qwen/Qwen-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen-VL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/Qwen-VL", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen-VL", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use Qwen/Qwen-VL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/Qwen-VL" # 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-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Qwen/Qwen-VL
- SGLang
How to use Qwen/Qwen-VL 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-VL" \ --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-VL", "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-VL" \ --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-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use Qwen/Qwen-VL with Docker Model Runner:
docker model run hf.co/Qwen/Qwen-VL
Add ScreenSpot-Pro evaluation result (Qwen-VL-7B)
#14 opened 2 months ago
by
merve
[Data preparation code] Is there any code for data preparation?
🔥 3
#13 opened over 1 year ago
by
esaba
Sample code for inference in Google Colab? RuntimeError: "slow_conv2d_cuda" not implemented for 'Byte'
1
#12 opened almost 2 years ago
by
sanjeev-bhandari01
solve <SimSun.ttf> file loading issue
#11 opened almost 2 years ago
by
tardis123
Poor performance using huggingface qwenVL not chat
🔥 1
1
#10 opened almost 2 years ago
by
sqrti
Image url encoding issue: https://huggingface.co/Qwen/Qwen-VL/blob/main/modeling_qwen.py#L561
1
#9 opened about 2 years ago
by
zhangyu
Adding `safetensors` variant of this model
#8 opened about 2 years ago
by
SFconvertbot
Update tokenization_qwen.py for error ''QWenTokenizer' object has no attribute 'IMAGE_ST''
#7 opened about 2 years ago
by
iampanda
Update tokenization_qwen.py for error ''QWenTokenizer' object has no attribute 'IMAGE_ST''
#6 opened about 2 years ago
by
iampanda
Adding `safetensors` variant of this model
#5 opened over 2 years ago
by
SFconvertbot
Cannot convert to gguf
4
#4 opened over 2 years ago
by
alfie-ns
Update tokenization_qwen.py
#3 opened over 2 years ago
by
ShushengYang
Update README.md
#2 opened over 2 years ago
by
eltociear
Update modeling_qwen.py
#1 opened over 2 years ago
by
takatosp1