https://github.com/furk4neg3/ibm-transformer-fine-tuning-pytorch-huggingface

A project demonstrating fine-tuning techniques for large language models (LLMs) using PyTorch and Hugging Face’s SFTTrainer module. Covers data preparation, training loop implementation, task-specific fine-tuning, and performance evaluation with PyTorch and Hugging Face.
https://github.com/furk4neg3/ibm-transformer-fine-tuning-pytorch-huggingface

Last synced: about 2 months ago
JSON representation

A project demonstrating fine-tuning techniques for large language models (LLMs) using PyTorch and Hugging Face’s SFTTrainer module. Covers data preparation, training loop implementation, task-specific fine-tuning, and performance evaluation with PyTorch and Hugging Face.

• Host: GitHub
• URL: https://github.com/furk4neg3/ibm-transformer-fine-tuning-pytorch-huggingface
• Owner: furk4neg3
• Created: 2024-11-11T12:35:41.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-11T12:40:35.000Z (about 2 months ago)
• Last Synced: 2024-11-11T13:32:31.790Z (about 2 months ago)
• Language: Jupyter Notebook
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Fine-Tuning Transformers with PyTorch and Hugging Face

This project demonstrates the process of loading, fine-tuning, and evaluating large language models (LLMs) using PyTorch and Hugging Face’s tools. It includes task-specific fine-tuning using Hugging Face’s `SFTTrainer` module and implementing a custom supervised training loop in PyTorch to build high-performing NLP models for specific use cases.

## Note

The kernel crashes when it reaches the final cell in the code, preventing any output from being generated.

## Overview

This project covers:

- Loading pretrained LLMs from Hugging Face

- Implementing a custom supervised training loop in PyTorch

- Task-specific fine-tuning with the `SFTTrainer` module

- Model evaluation for optimized task performance

## Table of Contents

1. [Introduction](#introduction)

2. [Objectives](#objectives)

8. [Requirements](#requirements)

9. [References](#references)

## Introduction

This project introduces the process of fine-tuning large language models for specific NLP tasks using PyTorch and Hugging Face. By loading pretrained LLMs and fine-tuning them with the `SFTTrainer` module, this project demonstrates how to create powerful, task-specific language models and assess their performance.

## Objectives

By completing this project, you will:

1. Load pretrained LLMs and make inferences using Hugging Face

2. Fine-tune LLMs on task-specific data with `SFTTrainer`

3. Evaluate and compare model performance for various NLP tasks

## Requirements

- Python 3.7+

- PyTorch

- Hugging Face Transformers Library

## References

- [IBM AI Engineering Professional Certificate](https://www.coursera.org/professional-certificates/ai-engineer?)

- [Generative AI Engineering with LLMs Specialization](https://www.coursera.org/specializations/generative-ai-engineering-with-llms)

- [Generative AI Engineering and Fine-Tuning Transformers](https://www.coursera.org/learn/generative-ai-engineering-and-fine-tuning-transformers?specialization=generative-ai-engineering-with-llms)