Introduction to LLM Fine-Tuning
Chapter 1: Foundations of Model Customization
What is Fine-Tuning?
Pre-training vs. Fine-Tuning
When to Fine-Tune: An Analytical Framework
Overview of Fine-Tuning Strategies
The Role of Transfer Learning in LLMs
Setting Up Your Development Environment
Chapter 2: Data Preparation for Fine-Tuning
Sourcing and Selecting High-Quality Datasets
Instruction-Based vs. Conversational Data Formats
Data Cleaning and Preprocessing Techniques
Creating and Structuring Custom Datasets
Tokenization for Fine-Tuning
Hands-on Practical: Building a Fine-Tuning Dataset
Chapter 3: Full Parameter Fine-Tuning
The Mechanics of Full Fine-Tuning
Architectural Considerations for Full Fine-Tuning
Managing Computational Resources
Configuring Training Arguments and Hyperparameters
Monitoring Training: Loss and Metrics
Saving and Loading Fine-Tuned Models
Practice: Full Fine-Tuning on a Small-Scale Model
Chapter 4: Parameter-Efficient Fine-Tuning (PEFT)
Introduction to Parameter-Efficient Fine-Tuning
Low-Rank Adaptation (LoRA): Theory and Operation
Implementing LoRA with the PEFT Library
Quantization and its effect on Fine-Tuning (QLoRA)
Other PEFT Methods: A Brief Survey
Comparing PEFT and Full Fine-Tuning Trade-offs
Hands-on Practical: Fine-Tuning with LoRA
Chapter 5: Evaluation and Deployment
Defining Performance Metrics for Generative Tasks
Quantitative Evaluation: ROUGE, BLEU, and Perplexity
Qualitative Evaluation: Human-in-the-Loop Assessment
Building an Evaluation Pipeline
Strategies for Merging Adapters with the Base Model
Preparing Models for Inference
Practice: Evaluating a Fine-Tuned Model
Tokenization for Fine-Tuning
Was this section helpful?
- Preprocessing data: Tokenization, Hugging Face, 2023 (Hugging Face) - Official guide to tokenization within the Hugging Face Transformers library, detailing concepts like special tokens, padding, and truncation.
- Neural Machine Translation of Rare Words with Subword Units, Rico Sennrich, Barry Haddow, Alexandra Birch, 2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (Association for Computational Linguistics) DOI: 10.18653/v1/P16-1162 - Introduces Byte Pair Encoding (BPE), a subword tokenization algorithm foundational to many LLMs.
- Language Models are Unsupervised Multitask Learners, Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever, 2019 (OpenAI) - The paper introducing GPT-2, it outlines the model's architecture and the BPE tokenization approach it uses.
- Natural Language Processing with Transformers: Building Innovative Applications with Hugging Face, Lewis Tunstall, Leandro von Werra, and Mario Šafranko, 2022 (O'Reilly Media) - A practical resource covering data preparation, tokenization, and fine-tuning with the Hugging Face ecosystem.