Update README.md

README.md

@@ -1,13 +1,15 @@
----
-tags:
-- arabic
-- tokenizer
-- morphology
-- nlp
-license: apache-2.0
-language:
-- ar
----
+---
+tags:
+- arabic
+- tokenizer
+- morphology
+- nlp
+license: apache-2.0
+language:
+- ar
+datasets:
+- dataflare/arabic-dialect-corpus
+---
 
 # DF-Arc: Morphology-Aware Arabic Tokenizer
 
@@ -25,11 +27,11 @@ from transformers import AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained("dataflare/df-arc", trust_remote_code=True)
 
-text = "والكتابة بالعربية ممتعة جدا"
+text = "الكتابة بالعربية ممتعة جدا"
 tokens = tokenizer.tokenize(text)
 print(tokens)
 ```
 
 ## Citation
 If you use DF-Arc, please cite our paper:
-*The Arabic Token Tax: Quantifying Tokenization Inefficiency in Large Language Models* (Dataflare Lab, 2026).
+*The Arabic Token Tax: Quantifying Tokenization Inefficiency in Large Language Models* (Dataflare Lab, 2026).