/NLP-LLM-Basic-Applications

Natural Language Processing (NLP) and Large Language Models (LLM) and various basic applications.

Primary LanguageJupyter Notebook

| NLP | LLM | Basic | Applications |

Natural Language Processing (NLP) and Large Language Models (LLM) and various basic applications.

Learning

| Overview

This notebook provides a whirlwind tour of various applications using Large Language Models (LLMs) from Hugging Face. The notebook covers the following applications:

  • Summarization
  • Sentiment analysis
  • Translation
  • Zero-shot classification
  • Few-shot learning

The examples demonstrate how to leverage existing open-source and proprietary models available on Hugging Face models for various applications. The notebook also introduces simple prompt engineering techniques.

Additionally, it explores Hugging Face APIs in more detail, providing insights into configuring LLM pipelines.

Learning Objectives

  1. Use a variety of existing models for common applications.
  2. Understand basic prompt engineering.
  3. Differentiate between search and sampling for LLM inference.
  4. Familiarize yourself with key Hugging Face abstractions: datasets, pipelines, tokenizers, and models.