$ pip install cortex

# cluster.yaml
​
region: us-east-1
instance_type: g4dn.xlarge
min_instances: 1
max_instances: 3
spot: true

$ cortex cluster up --config cluster.yaml

$ mkdir text-generator && cd text-generator
$ touch predictor.py requirements.txt text_generator.yaml

# predictor.py
​
from transformers import pipeline
​
class PythonPredictor:
    def __init__(self, config):
        self.model = pipeline(task="text-generation")
​
    def predict(self, payload):
        return self.model(payload["text"])[0]

# requirements.txt
​
transformers
torch

# text_generator.yaml
​
- name: text-generator
  kind: RealtimeAPI
  predictor:
    type: python
    path: predictor.py
  compute:
    gpu: 1

$ cortex deploy text_generator.yaml

$ cortex get text-generator --watch

$ cortex logs text-generator

$ curl http://***.elb.us-west-2.amazonaws.com/text-generator -X POST -H "Content-Type: application/json" -d '{"text": "hello world"}'

$ cortex delete text-generator