Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Workflows distribuídos de AI com Elixir e Livebook
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Hugo Baraúna
September 28, 2024
Programming
140
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Workflows distribuídos de AI com Elixir e Livebook
Hugo Baraúna
September 28, 2024
More Decks by Hugo Baraúna
See All by Hugo Baraúna
The Architecture Behind Deploying Livebook Apps with Livebook Teams
hugobarauna
0
140
Visão geral sobre Elixir @ Elixir Carajás Meetup
hugobarauna
0
31
The Architecture Behind Deploying Livebook Apps with Livebook Teams
hugobarauna
0
150
A história por trás da criação do Elixir
hugobarauna
0
57
Using Livebook to build and deploy internal tools @ ElixirConf 2024
hugobarauna
0
520
Other Decks in Programming
See All in Programming
Vite+ Unified Toolchain for the Web
naokihaba
0
290
AI時代のUIはどこへ行く?その2!
yusukebe
21
7.1k
These Five Tricks Can Make Your Apps Greener, Cheaper, & Nicer
hollycummins
0
280
運用エージェントは "作る" から "育てる" へ - 記憶と自己進化の3層設計パターン / self-evolving-agents-three-layer-agent-design
gawa
12
3.6k
Developing with AI Agents — Codex, Claude Code & Cowork Practical Guide
x5gtrn
PRO
0
1.3k
代数的データ型って何が嬉しいの? #frontend_phpcon_do
kajitack
8
3.4k
Semantic Version 単位で戦略を柔軟に変えて、パッケージアップデートを自動化する
daitasu
0
220
技術記事、AIに書かせるか、自分で書くか? 〜それでも私が自分の手で書く理由〜 / #QiitaConference
jnchito
2
1.4k
LLM Plugin for Node-REDの利用方法と開発について
404background
0
170
ローカルLLMでどこまでコードが書けるか -拡張版 / How much code can be written on a local LLM Extended
kishida
10
3.1k
ADKを使って簡単にAIエージェントを作ってみよう
k1mu21
0
260
Oxcを導入して開発体験が向上した話
yug1224
4
310
Featured
See All Featured
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
2k
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
230
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
300
GraphQLの誤解/rethinking-graphql
sonatard
75
12k
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
2
570
Designing for Performance
lara
611
70k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
技術選定の審美眼(2025年版) / Understanding the Spiral of Technologies 2025 edition
twada
PRO
118
120k
Testing 201, or: Great Expectations
jmmastey
46
8.2k
Chasing Engaging Ingredients in Design
codingconduct
0
220
Rails Girls Zürich Keynote
gr2m
96
14k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
430
Transcript
Work fl ows Distribuídos de IA com Elixir e Livebook
By Hugo Baraúna (@hugobarauna)
Functional Concurrent Distributed {
livebook-dev/livebook
Work fl ows Fine tuning de um modelo 1 Inferência
usando um modelo 2
None
“Quantas dessas 1,500,000 patentes tem relevância pra gente”
“Temos um dataset de 8,000 patentes marcadas como relevantes ou
não”
Solução Treinar um modelo classi fi cador de patentes relevantes
para o cliente
Hugo Baraúna @hugobarauna Dev advocate @ Livebook 🥑 Eng. Computação
- Poli USP 💻 Co-fundador @ Plataformatec 🖇
Live coding
Próximos passos
Install Livebook https://livebook.dev
Livebook Neural Network Smart cells https://livebook.dev
AI GPU Clusters com Livebook & Fly.io https:// fl y.io/blog/ai-gpu-clusters-from-your-laptop-livebook/
Case de AI com Elixir https://youtu.be/5FlZHkc4Mq4
Livro sobre Machine Learning em Elixir https://pragprog.com/titles/smelixir/machine-learning-in-elixir/
Código das demos https://github.com/hugobarauna/livebook-notebooks/tree/main/sorry-dave
obrigado livebook-dev/livebook livebook.dev @livebookdev @hugobarauna