Update README.md

README.md

@@ -1,5 +1,19 @@
-tokenizer - BPE 30_522 vocab size
-model - Roberta 
+---
+language: 
+  - Tamil
+tags:
+- Tamil-Tokenizer
+- Tamil-language-model
+license: "apache-2.0"
+datasets:
+- oscar
+---
+
+
+# tokenizer - BPE 30_522 vocab size
+
+
+## model - Roberta 
         trained using MLM 
         OSCAR dataset
-        size 1000 lines 
+        train data size 5000 lines olly