Fill-Mask
Transformers
PyTorch
Safetensors
Faroese
xlm-roberta
Inference Endpoints
vesteinn commited on
Commit
aa14981
1 Parent(s): ad2a99e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +27 -0
README.md CHANGED
@@ -1,3 +1,30 @@
1
  ---
2
  license: agpl-3.0
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: agpl-3.0
3
+ datasets:
4
+ - vesteinn/FC3
5
+ - vesteinn/IC3
6
+ - mideind/icelandic-common-crawl-corpus-IC3
7
+ - DDSC/partial-danish-gigaword-no-twitter
8
+ - NbAiLab/NCC
9
+ language:
10
+ - fo
11
  ---
12
+
13
+ This is a Faroese language model, it was trained by adapting the (ScandiBERT-no-faroese)[https://huggingface.co/vesteinn/ScandiBERT-no-faroese] model on the (FC3 corpus)[https://huggingface.co/datasets/vesteinn/FC3] for 50 epochs.
14
+
15
+ If you find this model useful, please cite
16
+
17
+ ```
18
+ @inproceedings{snaebjarnarson-etal-2023-transfer,
19
+ title = "{T}ransfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese",
20
+ author = "Snæbjarnarson, Vésteinn and
21
+ Simonsen, Annika and
22
+ Glavaš, Goran and
23
+ Vulić, Ivan",
24
+ booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
25
+ month = "may 22--24",
26
+ year = "2023",
27
+ address = "Tórshavn, Faroe Islands",
28
+ publisher = {Link{\"o}ping University Electronic Press, Sweden},
29
+ }
30
+ ```