volume=$PWD/data # share a volume with the Docker container to avoid downloading weights every run
docker run --gpus all --shm-size 1g -p 8080:80 -v$volume:/data ghcr.io/huggingface/text-generation-inference:latest--model-id$model--num-shard$num_shard
docker run --gpus all --shm-size 1g -p 8080:80 -v$volume:/data ghcr.io/huggingface/text-generation-inference:0.7--model-id$model--num-shard$num_shard
```
**Note:** To use GPUs, you need to install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html). We also recommend using NVIDIA drivers with CUDA version 11.8 or higher.
