Hugging Face's logo

jonfd
/
electra-small-is-no

Transformers
PyTorch
TensorFlow
Icelandic
Norwegian
electra
pretraining
Model card Files
xet
 Community
Jón Daðason commited on
Commit
191173e
·
1 Parent(s): 2fafb1d

Updated README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -6,14 +6,14 @@ license: cc-by-4.0
6
  datasets:
7
  - igc
8
  - ic3
9
- - icc
10
  - mc4
11
  ---
12
 
13
  # Icelandic-Norwegian ELECTRA-Small
14
  This model was pretrained on the following corpora:
15
  * The [Icelandic Gigaword Corpus](http://igc.arnastofnun.is/) (IGC)
16
- * The [Icelandic Common Crawl Corpus](https://arxiv.org/abs/2201.05601) (IC3)
17
  * The [Icelandic Crawled Corpus](https://huggingface.co/datasets/jonfd/ICC) (ICC)
18
  * The [Multilingual Colossal Clean Crawled Corpus](https://huggingface.co/datasets/mc4) (mC4) - Icelandic and Norwegian text obtained from .is and .no domains, respectively
19
 
 
6
  datasets:
7
  - igc
8
  - ic3
9
+ - jonfd/ICC
10
  - mc4
11
  ---
12
 
13
  # Icelandic-Norwegian ELECTRA-Small
14
  This model was pretrained on the following corpora:
15
  * The [Icelandic Gigaword Corpus](http://igc.arnastofnun.is/) (IGC)
16
+ * The Icelandic Common Crawl Corpus (IC3)
17
  * The [Icelandic Crawled Corpus](https://huggingface.co/datasets/jonfd/ICC) (ICC)
18
  * The [Multilingual Colossal Clean Crawled Corpus](https://huggingface.co/datasets/mc4) (mC4) - Icelandic and Norwegian text obtained from .is and .no domains, respectively
19