orai-nlp
/

bert-medium-sw

Feature Extraction

Inference Endpoints

Model card Files Files and versions Community

GorkaUrbizu commited on May 12, 2023

Commit

803962b

•

1 Parent(s): 131cb71

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -7,7 +7,7 @@ language:
 BERT medium (cased) model trained on a subset of 125M tokens of cc100-Swahili for our work [Scaling Laws for BERT in Low-Resource Settings](https://youtu.be/dQw4w9WgXcQ) at ACL2023 Findings.
-The model has 51M parameters (8L), with a vocab size of 50K.
 It was trained for 500K steps with a sequence length of 512 tokens.

 BERT medium (cased) model trained on a subset of 125M tokens of cc100-Swahili for our work [Scaling Laws for BERT in Low-Resource Settings](https://youtu.be/dQw4w9WgXcQ) at ACL2023 Findings.
+The model has 51M parameters (8L), and a vocab size of 50K.
 It was trained for 500K steps with a sequence length of 512 tokens.