NLP with LLMs: Fine-tuning Models for Classification & Question Answering

Large Language Models (LLMs)    |    Expert
  • 12 videos | 1h 33m 43s
  • Includes Assessment
  • Earns a Badge
Rating 5.0 of 1 users Rating 5.0 of 1 users (1)
Fine-tuning in the context of text-based models refers to the process of taking a pre-trained model and adapting it to a specific task or dataset with additional training. This technique leverages the general language understanding capabilities acquired by the model during its initial extensive training on a large corpus of text and refines its abilities to perform well on a more narrowly defined task or domain-specific data. In this course, you will learn how to fine-tune a model for sentiment analysis, starting with the preparation of datasets optimized for this purpose. You will be guided through setting up your computing environment and preparing a BERT classifier for sentiment analysis. Next, you will discover how to structure text data and align named entity recognition (NER) tags with subword tokenization. You will build on this knowledge to fine-tune a BERT model specifically for NER, training it to accurately identify and classify entities within text. Finally, you will explore the domain of question answering, learning to handle the challenges of long contexts to extract precise answers from extensive texts. You will prepare QnA data for fine-tuning and utilize a DistilBERT model to create an effective QnA system.

WHAT YOU WILL LEARN

  • Discover the key concepts covered in this course
    Load and clean data for fine-tuning
    Set up a fine-tuning job
    Fine-tune a bert classifier
    Generate predictions with a fine-tuned model
    Load and clean text for named entity recognition (ner)
  • Align ner tags with subword tokens
    Fine-tune bert for ner
    Generate context-question pairs for qna
    Set up data for fine-tuning
    Fine-tune a distilbert model for qna
    Summarize the key concepts covered in this course

IN THIS COURSE

  • 1m 58s
    In this video, we will discover the key concepts covered in this course. FREE ACCESS
  • 8m 41s
    Learn how to load and clean data for fine-tuning. FREE ACCESS
  • Locked
    3.  Setting up for Fine-tuning a BERT Classifier
    9m 16s
    Find out how to set up a fine-tuning job. FREE ACCESS
  • Locked
    4.  Fine-tuning a BERT Model and Pushing to Hugging Face Hub
    10m 31s
    In this video, discover how to fine-tune a BERT classifier. FREE ACCESS
  • Locked
    5.  Getting Predictions from a Fine-tuned Model
    5m 47s
    In this video, find out how to generate predictions with a fine-tuned model. FREE ACCESS
  • Locked
    6.  Structuring Text for Named Entity Recognition
    9m 12s
    In this video, you will learn how to load and clean text for named entity recognition (NER). FREE ACCESS
  • Locked
    7.  Aligning NER Tags to Match Subword Tokenization
    8m 53s
    Discover how to align NER tags with subword tokens. FREE ACCESS
  • Locked
    8.  Fine-tuning a BERT Model for Named Entity Recognition
    7m 8s
    During this video, you will learn how to fine-tune BERT for NER. FREE ACCESS
  • Locked
    9.  Dealing with Long Contexts for Question Answering
    10m 43s
    In this video, discover how to generate context-question pairs for QnA. FREE ACCESS
  • Locked
    10.  Structuring QnA Data in the Right Format for Fine Tuning
    12m 38s
    In this video, find out how to set up data for fine-tuning. FREE ACCESS
  • Locked
    11.  Fine-tuning a DistilBERT Model for Question Answering
    5m 53s
    Find out how to fine-tune a DistilBERT model for QnA. FREE ACCESS
  • Locked
    12.  Course Summary
    3m 2s
    In this video, we will summarize the key concepts covered in this course. FREE ACCESS

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.

Digital badges are yours to keep, forever.