Code + tutorial on using PyTorch-Lightning + QLoRA/peft to fine tune a LLM from Huggingface

jjung · November 8, 2023, 7:35pm

Here is where the code and detailed explanations are:

zjohn77/lightning-mlflow-hf/blob/main/README.md

# 🔥 Build Your Custom AI/LLM With PyTorch Lightning

## Introduction

Processes and information are at the heart of every business. The vulnerability and
opportunity of this moment is the question of whether your business can automate your
processes using AI, and reap the rewards of doing so. ChatGPT, a general purpose AI, has
opened our eyes to what AI can do. What matters now is directing the power of AI to *your*
business problems and unlock the value of *your* proprietary data. In this document, I will
show you how.

## Table of Contents

1. [Overview of LLM Fine Tuning](#1-overview-of-llm-fine-tuning)
2. [Problem Background](#2-problem-background)
3. [Architecture of the AI System](#3-architecture-of-the-ai-system)
4. [Code Deep Dive](#4-code-deep-dive)
5. [Model Results](#5-model-results)
6. [Installation and Quick Start](#6-installation-and-quick-start)
7. [Contribute](#7-contribute)

This file has been truncated. show original

Topic		Replies	Views
How to fine-tune a pretrained LLM on custom code libraries? Beginners	2	3776	April 29, 2024
Training LLM using local application Community Calls	2	652	May 1, 2024
Hugging Face Trainer class with accelerate 🤗Accelerate	2	343	May 21, 2024
Deploying Fine-Tune Falcon 40B with QLoRA on Sagemaker Inference Error Amazon SageMaker	29	6670	January 8, 2024
Llama 2 7B fine-tuned with IA3 errors when performing inference 🤗Transformers	2	636	January 16, 2024

Code + tutorial on using PyTorch-Lightning + QLoRA/peft to fine tune a LLM from Huggingface

Related topics