AI Workshop: Fine Tune a 660 M model using Quantization, Lora and QLora
Hosted by Vijender P
Registration
About Event
We are in the last leg of our September AI FDE Cohort at Alumnx AI Labs and I am conducting crash bootcamp sessions for the Cohort participants.
This should help in consolidating their knowledge of AI Concepts and get Hands On experience in building AI Applications.
I thought I would open up one of the Hands On Workshop sessions on Fine Tuning a 660 Million Parameter model.
We will Fine Tune mBart50 a 660M Language Translation model using techniques like Quantization, Lora and QLora on an NVIDIA GPU in AWS.