MLOps Community
timezone
+00:00 GMT
Livestream
MLOps Community: LLMs Mini Summit
# Language Model Fine-tuning
# Large Language Models
# Weights and Biases

Unlock the secrets of maximizing language models' potential in our exclusive sessions that traverse the diverse landscapes of language model fine-tuning. Dive deep into the intricacies of the fine-tuning process, explore the best practices crucial for training large models, and witness real-world applications through the lens of the prestigious Kaggle competition.

Our sessions promise an insightful exploration of new evaluation paradigms, shedding light on how to truly comprehend what these models learn. Discover the answers to fundamental questions and challenges in fine-tuning, as seasoned experts share practical experiences, invaluable tips, and unique insights.

Don't miss this opportunity brought to us by Weights & Biases to expand your knowledge and harness the full potential of Language Models! Join us to gain an enriched understanding and learn to leverage these models effectively. Register now and be at the forefront of cutting-edge advancements in Language Model Fine-Tuning!

Speakers
Ben Epstein
Ben Epstein
Founding Software Engineer @ Galileo
Jonathan Whitaker
Jonathan Whitaker
AI Researcher @ Data Science Castnet
Boris Dayma
Boris Dayma
CEO @ Craiyon
Thomas Capelle
Thomas Capelle
ML Engineer @ Weights & Biases
Robbie McCorkell
Robbie McCorkell
Founding Engineer @ Leap Labs
Agenda
Track View
5:00 PM
5:05 PM
Stage 1
Opening / Closing
calendar
Intro
Ben Epstein
5:05 PM
5:25 PM
Stage 1
Presentation
calendar
What The Kaggle 'LLM Science Exam' Competition Can Teach Us About LLMs

This competition challenged participants to submit a model capable of answering science-related multiple-choice questions. In doing so it provided a fruitful environment for exploring most of the key techniques and approaches being applied today by anyone building with LLMs. In this talk, we'll look at some key lessons that this competition can teach us.

+ Read More
Jonathan Whitaker
5:25 PM
5:45 PM
Stage 1
Presentation
calendar
A Recipe for Training Large Language Models

AI models have become orders of magnitude larger in the last few years.

Training such large models presents new challenges, and has been mainly practiced in large companies.

In this talk, we tackle best practices for training large models, from early prototype to production.

+ Read More
Boris Dayma
5:45 PM
6:05 PM
Stage 1
Presentation
calendar
Deep Dive on LLM Fine-tune

In his session Thomas will focus on understanding the ins and outs of fine-tuning LLMs. We all have a lot of questions during the fine-tuning process. How do you prepare your data? How much data do you need? Do you need to use a high-level API, or can you do this in PyTorch? During this talk, we will try to answer these questions. Thomas will share some tips and tricks on his journey in the LLM fine-tuning landscape. What worked and what did not, and hopefully, you will learn from his experience and the mistakes he made.

+ Read More
Thomas Capelle
6:05 PM
6:25 PM
Stage 1
Presentation
calendar
Do you really know what your model has learned?

Leap Labs demonstrates how data-independent model evaluations represent a paradigm shift in the model development process. All through our dashboard’s beautiful Weights & Biases Weave integration.

+ Read More
Robbie McCorkell
6:25 PM
6:30 PM
Stage 1
Opening / Closing
calendar
Closing Dicussion
Ben Epstein
6:30 PM
6:45 PM
Stage 1
1:1 networking
calendar
Networking
Event has finished
November 16, 5:00 PM, GMT
Online
Organized by
MLOps Community
MLOps Community
Event has finished
November 16, 5:00 PM, GMT
Online
Organized by
MLOps Community
MLOps Community