Update README.md

README.md

@@ -13,4 +13,4 @@ tags:
 <img src="https://cdn-uploads.huggingface.co/production/uploads/62cf05b026c94b143172379c/jYm4W_5JCbcdZJemb3n0d.png"
      style="float:left;width:200px;height:200px;object-fit:cover;border-radius:50%;margin-right:16px;" />
 
-LAMB (**LA**tin **M**odern**B**ERT) is a ModernBERT base pre-trained on over **8B tokens**, nearly an order of magnitude more than previous Latin encoder models.
+LAMB (**LA**tin **M**odern**B**ERT) is a ModernBERT based model pre-trained on over **20B tokens**, more than an order of magnitude more than any previous Latin encoder models.