Data Free Knowledge Distillation On Qnli
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | Accuracy | Paper Title | Repository |
|---|---|---|---|
| ProGen (T5-base) | 85.9 | ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback | - |
| Prompt2Model (T5-base) | 62.2 | Prompt2Model: Generating Deployable Models from Natural Language Instructions | |
| ZeroGen (T5-base) | 88.5 | ZeroGen: Efficient Zero-shot Learning via Dataset Generation | |
| GOLD (T5-base) | 91.7 | GOLD: Generalized Knowledge Distillation via Out-of-Distribution-Guided Language Data Generation |
0 of 4 row(s) selected.