Update README.md
Browse files
README.md
CHANGED
|
@@ -3,10 +3,10 @@ language: es
|
|
| 3 |
license: mit
|
| 4 |
---
|
| 5 |
|
| 6 |
-
|
| 7 |
-
|
| 8 |
# ConvBERT small pre-trained on large_spanish_corpus
|
| 9 |
|
|
|
|
|
|
|
| 10 |
## Metrics on evaluation set
|
| 11 |
|
| 12 |
```
|
|
@@ -29,4 +29,7 @@ from transformers import AutoModel, AutoTokenizer
|
|
| 29 |
model_name = "mrm8488/convbert-small-spanish"
|
| 30 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 31 |
model = AutoModel.from_pretrained(model_name)
|
| 32 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
license: mit
|
| 4 |
---
|
| 5 |
|
|
|
|
|
|
|
| 6 |
# ConvBERT small pre-trained on large_spanish_corpus
|
| 7 |
|
| 8 |
+
The ConvBERT architecture is presented in the ["ConvBERT: Improving BERT with Span-based Dynamic Convolution"](https://arxiv.org/abs/2008.02496) paper.
|
| 9 |
+
|
| 10 |
## Metrics on evaluation set
|
| 11 |
|
| 12 |
```
|
|
|
|
| 29 |
model_name = "mrm8488/convbert-small-spanish"
|
| 30 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 31 |
model = AutoModel.from_pretrained(model_name)
|
| 32 |
+
```
|
| 33 |
+
|
| 34 |
+
> Created by [Manuel Romero/@mrm8488](https://twitter.com/mrm8488) with the support of [Narrativa](https://www.narrativa.com/)
|
| 35 |
+
> Made with <span style="color: #e25555;">♥</span> in Spain
|