from transformers import pipeline


class Model:
    def __init__(self, **kwargs):
        self._model = None

    def load(self):
        self._model = pipeline("text-classification")

    def predict(self, model_input):
        return self._model(model_input)

To complete model/model.py, we’ll implement model inference and invoke our finished model.

​
Run model inference

The Model.predict() function runs every time the model server is called.

We’ll use the text classification model in predict() and return the results:

model/model.py
def predict(self, model_input):
    return self._model(model_input)

​
Invoke your finished model

After truss watch shows that the server is updated, it’s time to invoke your finished model using truss predict in your terminal:

Invocation

truss predict -d '"Truss is awesome!"'

Response

[
  {
    "label": "POSITIVE",
    "score": 0.999873161315918
  }
]
Step 5: Implement model loadStep 7: Publish your Truss