Reader small image

You're reading from  Generative AI with Python and TensorFlow 2

Product typeBook
Published inApr 2021
PublisherPackt
ISBN-139781800200883
Edition1st Edition
Right arrow

Summary

In this chapter, we introduced some of the core ideas that have dominated recent models for NLP, like the attention mechanism, contextual embeddings, and self-attention. We then used this foundation to learn about the transformer architecture and its internal components. We briefly discussed BERT and its family of architectures.

In the next section of the chapter, we presented a discussion on the transformer-based language models from OpenAI. We discussed the architectural and dataset-related choices for GPT and GPT-2. We also used the transformer package from Hugging Face to develop our own GPT-2-based text generation pipeline. We finally closed the chapter with a brief discussion on the latest and greatest language model, GPT-3. We discussed various motivations behind developing such a huge model and its long list of capabilities, which go beyond the list of traditionally tested benchmarks.

This chapter, along with Chapter 9, The Rise of Methods for Text Generation...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Generative AI with Python and TensorFlow 2
Published in: Apr 2021Publisher: PacktISBN-13: 9781800200883