diff --git a/docker-compose.yml b/docker-compose.yml new file mode 100644 index 00000000..08fe8b35 --- /dev/null +++ b/docker-compose.yml @@ -0,0 +1,19 @@ +services: + text-generation-inference: + image: ghcr.io/huggingface/text-generation-inference:1.0.0 + ports: + - "8080:80" + volumes: + - ${HOME}/.cache:/root/.cache + working_dir: /app + container_name: text-generation-inference + ipc: host + deploy: + resources: + reservations: + devices: + - driver: "nvidia" + device_ids: ["0"] + capabilities: [gpu] + restart: unless-stopped + command: --model-id tiiuae/falcon-7b-instruct --huggingface-hub-cache /root/.cache/huggingface/hub