Reader small image

You're reading from  Transformers for Natural Language Processing - Second Edition

Product typeBook
Published inMar 2022
PublisherPackt
ISBN-139781803247335
Edition2nd Edition
Right arrow
Author (1)
Denis Rothman
Denis Rothman
author image
Denis Rothman

Denis Rothman graduated from Sorbonne University and Paris-Diderot University, designing one of the very first word2matrix patented embedding and patented AI conversational agents. He began his career authoring one of the first AI cognitive Natural Language Processing (NLP) chatbots applied as an automated language teacher for Moet et Chandon and other companies. He authored an AI resource optimizer for IBM and apparel producers. He then authored an Advanced Planning and Scheduling (APS) solution used worldwide.
Read more about Denis Rothman

Right arrow

Generic text completion with GPT-2

We will explore an example with a GPT-2 generic model from top to bottom. The goal of the example we will run is to determine the level of abstract reasoning a GPT model can attain.

This section describes the interaction with a GPT-2 model for text completion. We will focus on Step 9 of the OpenAI_GPT_2.ipynb notebook described in detail in Appendix III, Generic Text Completion with GPT-2.

You can first read this section to see how the generic pretrained GPT-2 model will react to a specific example. Then read Appendix III, Generic Text Completion with GPT-2, to go into the details of how a generic GPT-2 model is implemented in a Google Colab notebook.

You can also read Appendix III directly, which contains the interaction of Step 9 described below.

First, let’s understand the specific example of the pretrained GPT-2 being applied.

Step 9: Interacting with GPT-2

In this section, we will interact with the...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Transformers for Natural Language Processing - Second Edition
Published in: Mar 2022Publisher: PacktISBN-13: 9781803247335

Author (1)

author image
Denis Rothman

Denis Rothman graduated from Sorbonne University and Paris-Diderot University, designing one of the very first word2matrix patented embedding and patented AI conversational agents. He began his career authoring one of the first AI cognitive Natural Language Processing (NLP) chatbots applied as an automated language teacher for Moet et Chandon and other companies. He authored an AI resource optimizer for IBM and apparel producers. He then authored an Advanced Planning and Scheduling (APS) solution used worldwide.
Read more about Denis Rothman