deploy.yaml

---
version: "2.0"

services:
  app:
    image: yuravorobei/llama-2:0.6
    env:
      - "MAX_INPUT_TOKEN_LENGTH=256"
      - "MAX_NEW_TOKENS=50"

    command:
      - "bash"
      - "-c"
    args:
      - "uvicorn main:app --host 0.0.0.0 --port 7860"

    expose:
      - port: 7860
        as: 80
        to:
          - global: true

profiles:
  compute:
    app:
      resources:
        cpu:
          units: 4
        memory:
          size: 15Gi
        gpu:
          units: 1
          attributes:
            vendor:
              nvidia:

        storage:
          - size: 150Gi
  placement:
    akash:
      attributes:
      pricing:
        app:
          denom: uakt
          amount: 100000
deployment:
  app:
    akash:
      profile: app
      count: 1