Running inference on a fine-tuned model

In order to run inference against your trained model we have to promote it to the inference api.

client.fine_tuning.promote(id="ft-e9c8928d-ef90-44b5-a837-76d089924639")

This may take a few minutes.

Once done with the model we can demote it.

client.fine_tuning.demote(id="ft-e9c8928d-ef90-44b5-a837-76d089924639")