version: "3.8"

services:
  query_2_vec_Qwen3-Embedding-0.6B:
    image: ghcr.io/huggingface/text-embeddings-inference:1.8
    container_name: query_2_vec_Qwen3-Embedding-0.6B
    restart: unless-stopped
    entrypoint: /bin/bash
    command: |
      -c "bash /app/start_vllm.sh"
    shm_size: '45600m'
    ports:
      - "5010:8080"
    volumes:
      - .:/app
        #- ./../../../../data:/app/data
      - /home/hediehloo/code/embedding/embedding_model/train/qwen/output/v28-20251223-054407/merged-checkpoint-3707:/app/data/models/Qwen3-Embedding-0.6B/model
      # - ./../../../logging_config.json:/app/logging_config.json
      # - ./../../../src:/app/src
      # - ./../../../logs:/app/logs
    deploy:
      resources:
        reservations:
          devices:
            - capabilities: [gpu]
    stdin_open: true
    tty: true