Commit
•
9624ab4
1
Parent(s):
b435dba
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,14 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
widget:
|
| 3 |
- text: "I almost forgot to eat lunch.</s></s>I didn't forget to eat lunch."
|
| 4 |
- text: "I almost forgot to eat lunch.</s></s>I forgot to eat lunch."
|
| 5 |
- text: "I ate lunch.</s></s>I almost forgot to eat lunch."
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
This is an off-the-shelf roberta-large model finetuned on WANLI, the Worker-AI Collaborative NLI dataset ([Liu et al., 2022](https://arxiv.org/abs/2201.05955)). It outperforms the `roberta-large-mnli` model on seven out-of-domain test sets, including by 11% on HANS and 9% on Adversarial NLI.
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
tags:
|
| 5 |
+
- text-classification
|
| 6 |
widget:
|
| 7 |
- text: "I almost forgot to eat lunch.</s></s>I didn't forget to eat lunch."
|
| 8 |
- text: "I almost forgot to eat lunch.</s></s>I forgot to eat lunch."
|
| 9 |
- text: "I ate lunch.</s></s>I almost forgot to eat lunch."
|
| 10 |
+
datasets:
|
| 11 |
+
- alisawuffles/WANLI
|
| 12 |
---
|
| 13 |
|
| 14 |
This is an off-the-shelf roberta-large model finetuned on WANLI, the Worker-AI Collaborative NLI dataset ([Liu et al., 2022](https://arxiv.org/abs/2201.05955)). It outperforms the `roberta-large-mnli` model on seven out-of-domain test sets, including by 11% on HANS and 9% on Adversarial NLI.
|