Sari la conținutul principal

Fine-Tuning Your Own Llama 3 Model

Maxime, one of the world's leading thinkers in generative AI research, shows you how to fine-tune the Llama 3 LLM using Python and the Hugging Face platform.
Maxime Labonne
Maxime Labonne

Creează-ți contul gratuit

Practică și urmărește-ți progresul.

Continuă cu GoogleContinuând, accepți Termenii de utilizare, Politica de confidențialitate și faptul că datele tale sunt stocate în SUA.

Meta's Llama 3 is one of the most powerful open weights LLMs, and forms the basis of many commercial generative AI applications. Fine-tuning is a technique to get better performance from LLMs for specific use cases, and is fast becoming an essential skill for organizations making AI applications.

In this session, Maxime, one of the world's leading thinkers in generative AI research, shows you how to fine-tune the Llama 3 LLM using Python and the Hugging Face platform. You'll take a stock Llama 3 LLM, process data for training, then fine-tune the model, and evaluate its performance for an industry use case.

Key Takeaways:

  • Learn how to use Hugging Face Python packages to fine-tune LLMs.
  • Understand the workflow for customizing LLMs by fine-tuning.
  • Learn how to evaluate the success of your fine-tuned model.

Resources (including link to notebook)

Subiecte

Artificial IntelligenceGenerative AIPython

Conexe

Tutorial

Fine-Tuning Llama 3 and Using It Locally: A Step-by-Step Guide

Fine-Tune Llama 3.2

Tutorial

Fine-tuning Llama 3.2 and Using It Locally: A Step-by-Step Guide

Afișează mai mult →