How to Fine-tune the Llama 3.2 for Reasoning Capabilities at Lowest Cost

TIME STAMPS: 00:00 Intro 02:09 Introduction for Unsloth 03:45 Model and Dataset 05:47 Novita AI 07:36 Code Walkthrough USEFUL LINKS: Demo Source Code - https://github.com/yeyu2/Youtube_demos Tutorial on SubStack - https://yeyu.substack.com/p/how-to-fine-tune-the-llama-32-for?r=21aesy Novita AI - https://novita.ai/?ref=ngrmymz&utm_source=affiliate Unsloth - https://github.com/unslothai/unsloth Dataset - https://huggingface.co/datasets/KingNish/reasoning-base-20k MY CONNECT: Buy me a coffee - https://ko-fi.com/yeyuh Business inquiries - [email protected] X: https://x.com/Yeyu2HUANG Discord - http://discord.gg/KPTCE4CEmp Email subscription - https://yeyu.substack.com/ Exclusive service - https://ko-fi.com/yeyuh/commissions