Menu Navigation
Study PlannerJob DecodedBuildPilotInteractive PracticeLearning HubRoadmap ExplorerGlobal LeaderboardExams & PapersResearch DecodedArticlesPremium PlansAbout UsCareers
Create Custom Roadmap

LLM Fine-Tuning from Scratch

6 weeks
12 Learners
•
LLM Fine-Tuning from Scratch

Objective

“Master the complete fine-tuning pipeline from basics to covering tokenization, dataset curation, LoRA & QLoRA techniques, training on Hugging Face, evaluating model performance, and deploying your custom LLM via API.”

Topics

1.1
Introduction to Large Language Models (LLMs)
1.2
Understanding Tokenization
1.3
Hugging Face Tokenizers Library

Study Resources

→The Illustrated Transformer→Hugging Face Tokenizers Documentation→Tokenization for LLMs: A Comprehensive Guide
01

Learn

Watch curated videos and read study resources

02

Practice

Practice what you learned

03

Build Projects

Build projects using your new gained knowledge

04

Submit & Verify

Submit your project and get verified by our system

References

01The Illustrated Transformer
02Hugging Face Tokenizers Documentation
03Tokenization for LLMs: A Comprehensive Guide
04Hugging Face Datasets Documentation
05Deploying LLMs: A Practical Guide
06The Alpaca Dataset: A Strong, Replicable Instruction-Following Model
07PEFT: Parameter-Efficient Fine-Tuning of Foundation Models
08LoRA: Low-Rank Adaptation of Large Language Models
09QLoRA: Efficient Finetuning of Quantized LLMs
10Hugging Face Trainer Documentation
11Hugging Face Evaluate Library
12A Survey of Metrics for Evaluating LLMs
13Hugging Face Inference Endpoints
14FastAPI Documentation

Rate this roadmap

5.0
1 review

Help the community find high-signal technical paths.

Community Insights

0

Join the discussion

Sign in to share your thoughts and technical insights.

Loading insights...