Get in Touch
 Duration 14 hours

Course Outline

Introduction

  • Defining Large Language Models (LLMs).
  • Comparing LLMs with traditional NLP models.
  • An overview of LLM features and architectural design.
  • Exploring the challenges and limitations associated with LLMs.

Understanding LLMs

  • The complete lifecycle of an LLM.
  • Mechanisms behind LLM operation.
  • Key components of an LLM, including encoders, decoders, attention mechanisms, and embeddings.

Getting Started

  • Configuring the development environment.
  • Installing LLMs as development tools, such as Google Colab or Hugging Face.

Working with LLMs

  • Exploring the spectrum of available LLM options.
  • Creating and deploying an LLM.
  • Performing fine-tuning on a custom dataset.

Text Summarization

  • Understanding the task of text summarization and its practical applications.
  • Utilizing LLMs for both extractive and abstractive summarization.
  • Assessing summary quality using standard metrics such as ROUGE and BLEU.

Question Answering

  • Understanding the task of question answering and its use cases.
  • Applying LLMs to open-domain and closed-domain question answering.
  • Evaluating answer accuracy using metrics such as F1 and Exact Match (EM).

Text Generation

  • Understanding the task of text generation and its applications.
  • Using LLMs for conditional and unconditional text generation.
  • Controlling style, tone, and content through parameters such as temperature, top-k, and top-p.

Integrating LLMs with Other Frameworks and Platforms

  • Integrating LLMs with PyTorch or TensorFlow.
  • Building applications with Flask or Streamlit.
  • Deploying LLMs on Google Cloud or AWS.

Troubleshooting

  • Identifying and resolving common errors and bugs in LLMs.
  • Using TensorBoard to monitor and visualize the training process.
  • Leveraging PyTorch Lightning to streamline training code and enhance performance.
  • Utilizing Hugging Face Datasets for efficient data loading and preprocessing.

Summary and Next Steps

Requirements

  • A foundational understanding of natural language processing and deep learning.
  • Practical experience with Python and either PyTorch or TensorFlow.
  • Basic programming proficiency.

Audience

  • Software Developers.
  • NLP Enthusiasts.
  • Data Scientists.

Number of participants


Price per participant (excl. VAT)

Upcoming Courses

Related Categories