julien-c HF staff commited on
Commit
d28f8a8
1 Parent(s): 039753c

Migrate model card from transformers-repo

Browse files

Read announcement at https://discuss.huggingface.co/t/announcement-all-model-cards-will-be-migrated-to-hf-co-model-repos/2755
Original file history: https://github.com/huggingface/transformers/commits/master/model_cards/Geotrend/bert-base-en-fr-cased/README.md

Files changed (1) hide show
  1. README.md +50 -0
README.md ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: multilingual
3
+
4
+ datasets: wikipedia
5
+
6
+ license: apache-2.0
7
+
8
+ widget:
9
+ - text: "Google generated 46 billion [MASK] in revenue."
10
+ - text: "Paris is the capital of [MASK]."
11
+ - text: "Algiers is the largest city in [MASK]."
12
+ - text: "Paris est la [MASK] de la France."
13
+ - text: "Paris est la capitale de la [MASK]."
14
+ - text: "L'élection américaine a eu [MASK] en novembre 2020."
15
+ ---
16
+
17
+ # bert-base-en-fr-cased
18
+
19
+ We are sharing smaller versions of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) that handle a custom number of languages.
20
+
21
+ Unlike [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased), our versions give exactly the same representations produced by the original model which preserves the original accuracy.
22
+
23
+ For more information please visit our paper: [Load What You Need: Smaller Versions of Multilingual BERT](https://www.aclweb.org/anthology/2020.sustainlp-1.16.pdf).
24
+
25
+ ## How to use
26
+
27
+ ```python
28
+ from transformers import AutoTokenizer, AutoModel
29
+
30
+ tokenizer = AutoTokenizer.from_pretrained("Geotrend/bert-base-en-fr-cased")
31
+ model = AutoModel.from_pretrained("Geotrend/bert-base-en-fr-cased")
32
+
33
+ ```
34
+
35
+ To generate other smaller versions of multilingual transformers please visit [our Github repo](https://github.com/Geotrend-research/smaller-transformers).
36
+
37
+ ### How to cite
38
+
39
+ ```bibtex
40
+ @inproceedings{smallermbert,
41
+ title={Load What You Need: Smaller Versions of Mutlilingual BERT},
42
+ author={Abdaoui, Amine and Pradel, Camille and Sigel, Grégoire},
43
+ booktitle={SustaiNLP / EMNLP},
44
+ year={2020}
45
+ }
46
+ ```
47
+
48
+ ## Contact
49
+
50
+ Please contact amine@geotrend.fr for any question, feedback or request.