cog.yaml

# Configuration for Cog ⚙️
# Reference: https://github.com/replicate/cog/blob/main/docs/yaml.md

build:
  # set to true if your model requires a GPU
  gpu: true
  cuda: "11.7"

  # python version in the form '3.8' or '3.8.12'
  python_version: "3.8"
  

  # a list of packages in the format <package-name>==<version>
  python_packages:
    - "numpy==1.24.2"
    - "torch==2.0"
    - "accelerate==0.18.0"
    - "peft==0.2.0"
    - "sentencepiece==0.1.97"
    - "tensorizer==1.0.1"
    - "jinja2==3.1.2"
    - "deepspeed==0.8.3"

  run:
  # speed up downloading weights with gcloud storage cp
  - "echo 'deb [signed-by=/usr/share/keyrings/cloud.google.gpg] https://packages.cloud.google.com/apt cloud-sdk main' | tee -a /etc/apt/sources.list.d/google-cloud-sdk.list"
  - "curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | apt-key --keyring /usr/share/keyrings/cloud.google.gpg add -"
  - "apt-get update && apt-get install google-cloud-cli"
    

# predict.py defines how predictions are run on your model
predict: "predict.py:Predictor"