Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

CodeSignal

Harnessing Transformers with Hugging Face

via CodeSignal

Go to class Write review

Overview

You'll explore the powerful Hugging Face ecosystem and master different pre-trained Transformer architectures, understanding the specific characteristics of BERT, GPT-2, and T5 models along with their tokenizers and use cases.

Syllabus

  • Unit 1: Introduction to Hugging Face
    • Your First Sentiment Analysis Pipeline
    • Building Your First Text Generator
    • Building Question Answering Pipeline
    • Working with Core Transformer Components
  • Unit 2: BERT Encoder Architecture
    • Exploring BERT Tokenizer Fundamentals
    • BERT Fills in the Blanks
    • Context Changes Everything in BERT
    • Building Your First BERT Classifier
  • Unit 3: GPT-2 Autoregressive Generation
    • GPT-2 Tokenization Pattern Analysis
    • Fixing GPT-2 Text Generation Issues
    • Inside GPT-2 Decision Making
    • Creative versus Predictable Text Generation
  • Unit 4: T5 Encoder Decoder Mastery
    • T5 Tokenizer Bug Hunt
    • Building Universal Text Processor
    • Perfecting T5 Text Generation
    • T5 Model Architecture Explorer
    • Building Your T5 Task Handler

Reviews

Start your review of Harnessing Transformers with Hugging Face

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.