DeeplearningAI Organizes Free Workshop on "Efficient Fine-Tuning for Llama-7b on a Single GPU"

Image source: Analytics Drift

DeeplearningAI is organizing a free workshop called "Efficient Fine-Tuning for Llama-7b on a Single GPU" on 28 August from 10:30-11:30 pm IST. The workshop will be completely online.

Image source: Eventbrite

In this hands-on workshop, the hosts, through a demo, will discuss the unique challenges in fine-tuning LLMs and show learners how they can tackle these challenges with open-source tools.

Image source: Canva

Piero Molino, the co-founder and CEO of Predibase, and Travis Addair, co-founder and CTO of Predibase, will host the workshop.

Image source: Eventbrite

Through this session, attendees will learn how to fine-tune LLMs like Llama-2-7b on a single GPU. They will also learn techniques like parameter efficient tuning and quantization, and how they can help.

Image source: Meta

Hosts will also discuss how to train a 7b param model on a single T4 GPU (QLoRA), how to deploy tuned models like Llama-2 to production, and how to use RAG to do question answering with trained LLMs.

Image source: Canva

This workshop will equip machine learning engineers to unlock the capabilities of large language models like Llama-2 for their own projects.

Image source: Canva

Join our WhatsApp Channel Now!

Get the latest updates on AI developments.

Produced by: Sahil Pawar Designed by: Prathamesh