Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,13 @@ tags:
|
|
| 4 |
model-index:
|
| 5 |
- name: electra-nli_finetuned
|
| 6 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
@@ -13,8 +20,8 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
The model base is [electra-small](google/electra-small-discriminator).
|
| 15 |
It has been fine-tuned on: [snli](https://huggingface.co/datasets/snli), [scitail](https://huggingface.co/datasets/scitail),
|
| 16 |
-
[wanli](https://huggingface.co/datasets/alisawuffles/WANLI),
|
| 17 |
-
[
|
| 18 |
|
| 19 |
|
| 20 |
|
|
@@ -41,7 +48,7 @@ snli: 89.15
|
|
| 41 |
scitail: 90.08%
|
| 42 |
wanli: 67.84%
|
| 43 |
mnli: 81.95%
|
| 44 |
-
|
| 45 |
anli-r1_test: 46.60%
|
| 46 |
anli-r2_test: 42.50%
|
| 47 |
anli-r3_test: 43.08%
|
|
@@ -51,4 +58,4 @@ anli-r3_test: 43.08%
|
|
| 51 |
|
| 52 |
- Transformers 4.31.0
|
| 53 |
- TensorFlow 2.12.0
|
| 54 |
-
- Tokenizers 0.13.3
|
|
|
|
| 4 |
model-index:
|
| 5 |
- name: electra-nli_finetuned
|
| 6 |
results: []
|
| 7 |
+
datasets:
|
| 8 |
+
- snli
|
| 9 |
+
- scitail
|
| 10 |
+
- multi_nli
|
| 11 |
+
- alisawuffles/WANLI
|
| 12 |
+
- pietrolesci/nli_fever
|
| 13 |
+
- anli
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
|
|
|
| 20 |
|
| 21 |
The model base is [electra-small](google/electra-small-discriminator).
|
| 22 |
It has been fine-tuned on: [snli](https://huggingface.co/datasets/snli), [scitail](https://huggingface.co/datasets/scitail),
|
| 23 |
+
[wanli](https://huggingface.co/datasets/alisawuffles/WANLI), [mnli](https://huggingface.co/datasets/multi_nli),
|
| 24 |
+
[fever_nli](https://huggingface.co/datasets/pietrolesci/nli_fever), [anli](https://huggingface.co/datasets/anli).
|
| 25 |
|
| 26 |
|
| 27 |
|
|
|
|
| 48 |
scitail: 90.08%
|
| 49 |
wanli: 67.84%
|
| 50 |
mnli: 81.95%
|
| 51 |
+
nli_fever: 74.14%
|
| 52 |
anli-r1_test: 46.60%
|
| 53 |
anli-r2_test: 42.50%
|
| 54 |
anli-r3_test: 43.08%
|
|
|
|
| 58 |
|
| 59 |
- Transformers 4.31.0
|
| 60 |
- TensorFlow 2.12.0
|
| 61 |
+
- Tokenizers 0.13.3
|