emillykkejensen commited on
Commit
4bef8aa
1 Parent(s): 1915e40

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -1
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 including only Danish embeddings.
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)