Completed
53:43 – Closing and what’s next
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Finetuning LLMs on Strix Halo - Full, LoRA, and QLoRA on Gemma-3, Qwen-3, and GPT-OSS-20B
Automatically move to the next video in the Classroom when playback concludes
- 1 00:00 – Intro and goals
- 2 04:09 – Strix Halo Finetuning Toolbox Installation
- 3 10:49 – Gemma-3 Notebook Introduction
- 4 16:57 – Setup, Imports and Dataset
- 5 20:36 – Gemma-3-1B Full Parameter Finetuning
- 6 26:28 – Loading Finetuned Model for Inference
- 7 28:21 – Gemma-3-12B Full Parameter Finetuning
- 8 30:00 – LoRA Finetuning
- 9 37:30 – LoRA and QLoRA on Gemma-3 8 and 4-bit
- 10 43:08 – GPT-OSS 20B Finetuning with LoRA
- 11 48:13 – GPT-OSS 20B Finetuning with Reasoning Harmony Template
- 12 53:43 – Closing and what’s next