Context and completion examples

In this section, we will interact with a GPT-2 117M model trained on our dataset. We will first generate an unconditional sample that requires no input on our part. Then we will enter a context paragraph to obtain a conditional text completion response from our trained model.

Let's first run an unconditional sample:

#@title Step 11: Generating Unconditional Samples
import os # import after runtime is restarted
os.chdir("/content/gpt-2/src")
!python generate_unconditional_samples.py --model_name '117M'

You will not be prompted to enter context sentences since this is an unconditional sample generator.

To stop the cell, double-click on the run button of the cell or type Ctrl + M.

The result is random but makes sense from a grammatical perspective. From a semantic point of view, the result is not as interesting because we provided no context. But still, the process is remarkable. It invents posts, writes a...