Commit
•
4bef8aa
1
Parent(s):
1915e40
Update README.md
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ language:
|
|
4 |
license: apache-2.0
|
5 |
---
|
6 |
## daT5-base
|
7 |
-
A smaller version of google/mt5-base
|
8 |
|
9 |
## How to use
|
10 |
```python
|
@@ -12,3 +12,12 @@ from transformers import AutoTokenizer, AutoModel
|
|
12 |
tokenizer = AutoTokenizer.from_pretrained("emillykkejensen/daT5-base")
|
13 |
model = AutoModel.from_pretrained("emillykkejensen/daT5-base")
|
14 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
license: apache-2.0
|
5 |
---
|
6 |
## daT5-base
|
7 |
+
A smaller version of [Google's mt5-base](https://huggingface.co/google/mt5-base) model, where the original model is reduced to only include Danish embeddings.
|
8 |
|
9 |
## How to use
|
10 |
```python
|
|
|
12 |
tokenizer = AutoTokenizer.from_pretrained("emillykkejensen/daT5-base")
|
13 |
model = AutoModel.from_pretrained("emillykkejensen/daT5-base")
|
14 |
```
|
15 |
+
|
16 |
+
## Further reading
|
17 |
+
|
18 |
+
[Gist](https://gist.github.com/emillykkejensen/8bf1b323495efc7252dee966e6bc1b5c) showing (in Danish) how the embeddings are extracted
|
19 |
+
|
20 |
+
[Article](https://towardsdatascience.com/how-to-adapt-a-multilingual-t5-model-for-a-single-language-b9f94f3d9c90) explaining how to do it by [David Dale](https://huggingface.co/cointegrated)
|
21 |
+
|
22 |
+
## Also check out
|
23 |
+
[daT5-large](https://huggingface.co/emillykkejensen/daT5-large)
|