Créer un compteSe connecter

Recherches récentes

Aucune recherche récente

Options de recherche

Disponible uniquement lorsque vous êtes connecté.
mastouille.fr est l'un des nombreux serveurs Mastodon indépendants que vous pouvez utiliser pour participer au fédiverse.
Mastouille est une instance Mastodon durable, ouverte, et hébergée en France.

Administré par :

Statistiques du serveur :

655
comptes actifs

mastouille.fr: À proposAnnuaire des profilsPolitique de confidentialité

Mastodon: À proposTélécharger l’applicationRaccourcis clavierVoir le code sourcev4.3.4

#finetuning

0 message0 participant0 message aujourd’hui
Public
Erik Jonker

Good news, a pity that they compared with GPT-3.5 but it will probably also be true for the next generation of models.
"Our analysis shows that fine-tuning improves the performance of open-source LLMs, allowing them to match or even surpass zero-shot GPT 3.5 and GPT-4, though still lagging behind fine-tuned GPT
3.5. "
link.springer.com/article/10.1
#opensource #LLM #AI #finetuning

SpringerLinkOpen-source LLMs for text annotation: a practical guide for model setting and fine-tuning - Journal of Computational Social ScienceThis paper studies the performance of open-source Large Language Models (LLMs) in text classification tasks typical for political science research. By examining tasks like stance, topic, and relevance classification, we aim to guide scholars in making informed decisions about their use of LLMs for text analysis and to establish a baseline performance benchmark that demonstrates the models’ effectiveness. Specifically, we conduct an assessment of both zero-shot and fine-tuned LLMs across a range of text annotation tasks using news articles and tweets datasets. Our analysis shows that fine-tuning improves the performance of open-source LLMs, allowing them to match or even surpass zero-shot GPT $$-$$ - 3.5 and GPT-4, though still lagging behind fine-tuned GPT $$-$$ - 3.5. We further establish that fine-tuning is preferable to few-shot training with a relatively modest quantity of annotated text. Our findings show that fine-tuned open-source LLMs can be effectively deployed in a broad spectrum of text annotation applications. We provide a Python notebook facilitating the application of LLMs in text annotation for other researchers.
Public *
Toni Aittoniemi

Cybertruck, the pro Russia truck!

PS. #ai screen reading is already actively thwarting political expression.

Instead of citing the text that’s written in this image word-for-word, the #systemprompts and #finetuning for this MLL instead truncate it as: ”political reasons”.

This is the ”brave new world” we are stepping into. Machine learning parsing the world into what it’s not.

The image shows a mobile webpage prompting a user to cancel their Tesla Cybertruck order. It includes the reservation number and asks for the reason for cancellation, with an option for "Reason not listed." The user provides additional feedback: Russian ships keep launching cruise missiles at Ukraine, while Musk did not let Ukraine sink this navy. Someone show him the dead civilians, please. I will take my money elsewhere.
ExplorerFlux en direct
À propos