version: '3'

version: '3'

services: alpaca-lora: build: context: ./ dockerfile: Dockerfile args: BUILDKIT_INLINE_CACHE: "0" image: alpaca-lora shm_size: '64gb' command: generate.py --load_8bit --base_model $BASE_MODEL --lora_weights 'tloen/alpaca-lora-7b' restart: unless-stopped volumes: - alpaca-lora:/root/.cache # Location downloaded weights will be stored ports: - 7860:7860 deploy: resources: reservations: devices: - driver: nvidia count: all capabilities: [ gpu ]

volumes: alpaca-lora: name: alpaca-lora