Few Shot Learning On Glue Qqp
Metriken
F1-score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | F1-score | Paper Title | Repository |
|---|---|---|---|
| DART | 67.8(3.2) | Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners |
0 of 1 row(s) selected.