Update README.md

README.md

@@ -7,11 +7,9 @@ language:
 
 BERT base (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 124M parameters (12L), with a vocab size of 50K.
+The model has 124M parameters (12L), and a vocab size of 50K.
 It was trained for 500K steps with a sequence length of 512 tokens.
 
-A bert-medium and bert-mini (8 and 4L) models are available at our [GitHub](https://github.com/orai-nlp/low-scaling-laws/tree/main/models).
-
 
 Authors
 -----------