May 2026
Intermediate
340 pages
9h 55m
French
book
Les grands modèles linguistiques : Les parties difficiles (French Edition)
by Thársis T. P. Souza, Jonathan K. Regenstein
Content preview from Les grands modèles linguistiques : Les parties difficiles (French Edition)
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Chapitre 3. Outilsd'évaluation pour les applications basées sur les LLM
Cet ouvrage a été traduit à l'aide de l'IA. Tes réactions et tes commentaires sont les bienvenus : translation-feedback@oreilly.com
On façonne nos outils et par la suite nos outils nous façonnent.
Père John Culkin (souvent attribué à Marshall McLuhan)
Passons maintenant à trois outils qui nous aident à faire évoluer notre travail d'évaluation : LangSmith, Promptfoo et LightEval. LangSmith facilite l'évolution et la surveillance des pipelines que nous avons abordés au chapitre 2. Promptfoo reprend ce concept d'évolutivité et le rend facile à appliquer à l'ensemble du domaine des prompts. LightEval, développé par Hugging Face, nous plonge dans l’évaluation de modèles de type benchmark à travers des tâches standardisées. À la fin de ce chapitre, tu auras une bonne maîtrise de la mise à l’échelle des évaluations de modèles, de prompts et de benchmarks. Parmi ces trois outils, Promptfoo et LightEval sont open source, contrairement à LangSmith. Bien que ce livre privilégie les outils open source, on inclut LangSmith car il est largement utilisé dans la pratique et offre un point de comparaison utile avec les alternatives open source.
LangSmith
LangSmith est un framework de développement qui fournit des outils complets pour créer, tester, surveiller et évaluer les LLMs et les LLMBA. Il permet aux équipes de suivre les performances des modèles, d’identifier les problèmes en production et d’améliorer en continu les ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.