Looking for a way to finetune your Large Language Models in an efficient, reproducible and scalable way? Want to use Llama or Mixtral to make your small models better? You have come to the right place! Meet Instructlab! the original github repo the code that I used Timestamps: 00:00 - Intro 01:17 - What is Instructlab? 02:42 - Concept 1: Trainingdata as taxonomy 06:28 - Concept 2: Synthetic data generation 07:44 - Concept 3: Mulit-phase trainign 08:45 - Demo: Setup in the cloud 11:39 - Demo: Adding our own data 13:20 - Demo: Test the untrained model 14:30 - Demo: Generate synthetic data 16:00 - Demo: Training our own model 16:40 - Demo: Testing the trained model 17:49 - Outro