Update README.md

This is a distilled version of BERT fine tuned on Banking77 data for classification purposes. The original model (BERT based classifier) was 483 MB but the distilled model (tinyBERT based) is approx 54MB in size. Accuracy of teacher model was 92+% while the distilled model achieved 86.5% accuracy

README.md

@@ -1,3 +1,11 @@
----
-license: cc
----
+---
+license: cc
+datasets:
+- mteb/banking77
+language:
+- en
+metrics:
+- accuracy
+base_model:
+- huawei-noah/TinyBERT_General_4L_312D
+---