Instructions to use 4bit/Qwen-VL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 4bit/Qwen-VL with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="4bit/Qwen-VL", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("4bit/Qwen-VL", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use 4bit/Qwen-VL with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "4bit/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": "4bit/Qwen-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/4bit/Qwen-VL
- SGLang
How to use 4bit/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 "4bit/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": "4bit/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 "4bit/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": "4bit/Qwen-VL", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use 4bit/Qwen-VL with Docker Model Runner:
docker model run hf.co/4bit/Qwen-VL
Ctrl+K
- 1.52 kB
- 21.4 kB
- 1.16 kB
- 2.09 kB
- 218 Bytes
- 1.96 GB xet
- 1.93 GB xet
- 1.93 GB xet
- 1.99 GB xet
- 1.92 GB xet
- 1.93 GB xet
- 1.93 GB xet
- 1.98 GB xet
- 1.99 GB xet
- 1.73 GB xet
- 83.4 kB
- 44.2 kB
- 1.96 GB xet
- 1.93 GB xet
- 1.93 GB xet
- 1.99 GB xet
- 1.92 GB xet
- 1.93 GB xet
- 1.93 GB xet
- 1.98 GB xet
- 1.99 GB xet
- 1.73 GB xet
- 79.9 kB
- 2.56 MB
- 14.9 kB
- 21.5 kB
- 173 Bytes
- 14.5 kB