« Drag-and-Drop LLMs » : différence entre les versions
(Page créée avec « ==en construction== == Définition == XXXXXXXXX == Français == ''' XXXXXXXXX ''' == Anglais == '''Drag-and-Drop LLMs''' LoRA, a parameter-efficient finetuning method for large language models, underperforms full finetuning in target domains but provides better regularization and maintains diverse generation compared to other techniques. == Source == [https://huggingface.co/papers/2506.16406 Source : huggingface] Catégorie:vocabulary ») |
Aucun résumé des modifications |
||
| Ligne 12 : | Ligne 12 : | ||
LoRA, a parameter-efficient finetuning method for large language models, underperforms full finetuning in target domains but provides better regularization and maintains diverse generation compared to other techniques. | LoRA, a parameter-efficient finetuning method for large language models, underperforms full finetuning in target domains but provides better regularization and maintains diverse generation compared to other techniques. | ||
== | == Sources == | ||
[https://huggingface.co/papers/2506.16406 Source : huggingface] | [https://huggingface.co/papers/2506.16406 Source : huggingface] | ||
[https://github.com/sanowl/Drag-and-Drop-LLMs-Zero-Shot-Prompt-to-Weights Source : GitHub] | |||
[[Catégorie:vocabulary]] | [[Catégorie:vocabulary]] | ||
Dernière version du 7 juillet 2025 à 14:33
en construction
Définition
XXXXXXXXX
Français
XXXXXXXXX
Anglais
Drag-and-Drop LLMs
LoRA, a parameter-efficient finetuning method for large language models, underperforms full finetuning in target domains but provides better regularization and maintains diverse generation compared to other techniques.
Sources
