Explore the process of creating a LeetCode dataset and fine-tuning a Phi-3 3.8B model using Unsloth in this 20-minute video tutorial. Learn how to generate a LeetCode dataset, convert text to JSON format, and implement fine-tuning techniques with Unsloth. Discover the baseline performance on LeetCode problems, observe the fine-tuning process, and evaluate the results through testing. Gain insights into dataset generation, model fine-tuning, and performance assessment for improving LeetCode problem-solving capabilities.
Fine-tuning Phi-3 for LeetCode: Dataset Generation and Unsloth Implementation
All About AI via YouTube
Overview
Syllabus
Intro
LeetCode Dataset Generation
Text to JSON Dataset Script
phi3 Fine-tuning Unsloth
LeetCode Problem Baseline
phi3 fine-tuning done
phi3 leetcode testing
conclusion
Taught by
All About AI
Related Courses
-
Pretraining LLMs
-
Fine-Tuning ChatGPT 3.5 with Synthetic Data from GPT-4 - Step-by-Step Guide
-
Fine-Tuning Llama 3 on a Custom Dataset for RAG Q&A - Training LLM on a Single GPU
-
Synthetic Data Generation and Fine-tuning for OpenAI GPT-4 or Llama 3
-
How to Fine-Tune a GPT-3 Model - Step by Step
-
Fine-tuning LLMs - Every Step Explained for Memorization Tasks
