docker run --rm \
  --gpus all \
  -p 8000:8000 \
  -v ~/.cache/huggingface:/root/.cache/huggingface \
  -e HUGGING_FACE_HUB_TOKEN=<your_hf_token> \
  vllm/vllm-openai:latest \
  --model mistralai/Mistral-7B-v0.1

        __
        __