« Peaufinage de l'espace latent » : différence entre les versions
Aucun résumé des modifications |
Aucun résumé des modifications |
||
Ligne 1 : | Ligne 1 : | ||
== En chantier == | |||
== Définition == | == Définition == | ||
Ligne 9 : | Ligne 10 : | ||
== Anglais == | == Anglais == | ||
''' representation fine-tuning ''' | ''' representation fine-tuning ''' | ||
<!-- PYREFT, a representation fine-tuning (ReFT) library that supports adapting internal language model representations via trainable interventions. With fewer fine-tuning parameters and more robust performance, pyreft can boost fine-tuning efficiency, decrease fine-tuning cost, while opening the doors to study the interpretability of adapting parameters. --> | <!-- PYREFT, a representation fine-tuning (ReFT) library that supports adapting internal language model representations via trainable interventions. With fewer fine-tuning parameters and more robust performance, pyreft can boost fine-tuning efficiency, decrease fine-tuning cost, while opening the doors to study the interpretability of adapting parameters. --> | ||
== Source == | == Source == |
Version du 18 juin 2024 à 13:15
En chantier
Définition
Français
peaufinage de représentations
peaufinage d'espace latent
Anglais
representation fine-tuning
Source
ReFT: Representation Finetuning for Language Models, Wu et al. (2024)
ReFT: Representation Finetuning for Language Models, Shaoni Mukherjee (2024)
Contributeurs: Claude Coulombe, Patrick Drouin, wiki