Update README.md

README.md

@@ -1,4 +1,4 @@
-This model is further trained on top of scibert-base using masked language modeling loss (MLM). The corpus is roughly 270,000 earth science-based publications.
+This model is further trained on top of scibert-base using masked language modeling loss (MLM). The corpus is roughly abstracts from 270,000 earth science-based publications.
 
 The tokenizer used is AutoTokenizer, which is trained on the same corpus.