services: text-generation-webui-docker: image: atinoda/text-generation-webui:default-nvidia # Specify variant as the :tag container_name: text-generation-webui environment: - EXTRA_LAUNCH_ARGS="--listen --verbose" # Custom launch args (e.g., --model MODEL_NAME) # - BUILD_EXTENSIONS_LIVE="coqui_tts whisper_stt" # Install named extensions during every container launch. THIS WILL SIGNIFICANLTLY SLOW LAUNCH TIME AND IS NORMALLY NOT REQUIRED. # - OPENEDAI_EMBEDDING_MODEL=intfloat/e5-large-v2 # Specify custom model for embeddings # - OPENEDAI_EMBEDDING_DEVICE=cuda # Specify processing device for embeddings ports: - 7860:7860 # Default web port # - 5000:5000 # Default API port # - 5005:5005 # Default streaming port volumes: - ./config/cache:/root/.cache # WARNING: Libraries may save large files here! - ./config/characters:/app/characters - ./config/instruction-templates:/app/instruction-templates - ./config/loras:/app/loras - ./config/models:/app/models # WARNING - very large files! - ./config/presets:/app/presets - ./config/prompts:/app/prompts - ./config/training:/app/training # - ./config/extensions:/app/extensions # Persist all extensions # - ./config/extensions/coqui_tts:/app/extensions/coqui_tts # Persist a single extension logging: driver: json-file options: max-file: "3" # number of files or file count max-size: "10M" ### HARDWARE ACCELERATION: comment or uncomment according to your hardware! ### ### CPU only ### # Nothing required - comment out the other hardware sections. ### Nvidia (default) ### deploy: resources: reservations: devices: - driver: nvidia device_ids: ['0'] capabilities: [gpu] ### AMD ROCM or Intel Arc ### # stdin_open: true # group_add: # - video # tty: true # ipc: host # devices: # - /dev/kfd # - /dev/dri # cap_add: # - SYS_PTRACE # security_opt: # - seccomp=unconfined