GenAI Cracow #2

ABSTRACT

Deconstructing the text embedding models

Selecting the optimal text embedding model is often guided by benchmarks such as the Massive Text Embedding Benchmark (MTEB). While choosing the best model from the leaderboard is a common practice, it may not always align perfectly with the unique characteristics of your specific dataset. This approach overlooks a crucial yet frequently underestimated element - the tokenizer.

We will delve deep into the tokenizer's fundamental role, shedding light on its operations and introducing straightforward techniques to assess whether a particular model is suited to your data based solely on its tokenizer. We will explore the significance of the tokenizer in the fine-tuning process of embedding models and discuss strategic approaches to optimize its effectiveness.

The details of the other sessions will be provided soon

BIO

Kacper Łukawski

Software developer and data scientist at heart, with an inclination to teach others. Public speaker, working in DevRel.

LinkedIn

Tomasz Stawarski

CEO @ Tequipy - a company that offers a seamless solution for equipping your team with the necessary hardware. Founder @ CyberCraft building the first brewery in Poland created by AI.

LinkedIn

Aleksander Piskorz

Almost 10 years as a tech journalist. Leveraging his insider perspective to help startups and executives unlock the potential of Generative AI.

LinkedIn

Sponsors

Codete is a software company based in Poland that specializes in custom software development and IT consulting. Codete in numbers:

- 350+ specialists

- 3 offices in Krakow, Lublin, Berlin, and coworking spaces in major Polish cities (Warsaw, Wroclaw, and Gdansk).

- 120+ projects

- 70+ clients from around the world

In January 2022 Codete opened its own resto-bar Techie’s where we host the best tech events in town.