Slow iteration cycles, inaccurate responses, and poor retrieval are just a few of the issues that currently plague the language models (LLMs) used today. So, how can you efficiently fine-tune and evaluate the performance of an LLM that powers your application?
In this hands-on workshop, you will fine-tune a popular open source LLM (Google’s Flan-T5) at scale using Ray and HuggingFace. Additionally, you will visualize and inspect your model predictions using Arize Phoenix.
You’ll learn about flexible and scalable approaches to fine-tuning. Then you’ll also learn how to visualize and analyze clusters of data points inside a notebook - with the ultimate goal of extracting tangible insights for fine-tuning an LLM to your own data, task, or desired response approach.
Learning Objectives:
Hands-on demonstration focused on scalable fine-tuning and inference of an open-source language model (Google's Flan-T5) in 40 minutes using Ray and HuggingFace. Workshop participants will have the opportunity to fine-tune their own Flan-T5 model in Colab.
Once fine-tuning is complete, use Phoenix to visualize the embedding distribution of our model before and after fine-tuning
** Please bring your laptop to follow along with this hands-on workshop.
---
Hosts: Arize AI & Anyscale
Agenda:
5:30pm - 6:00pm Arrival
6:00-7:30 - Hands-on workshop
7:30-8:00pm - Networking
---
Note: By RSVP'ing to this event, you are opting in to receive event updates and marketing communications from Arize AI and Anyscale according to their respective privacy policies: https://arize.com/privacy-policy/ https://www.anyscale.com/privacy-policy
