Update README.md

README.md

@@ -21,6 +21,7 @@ Has native thinking in **Hinglish and English.**
 Trained on v4-8 TPU 
 
 * Active Params : 1.7B (Including Embedding Layer)
+* Specialized [Tokenizer (fhai50032/QTK-81K)](https://huggingface.co/fhai50032/QTK-81K) For better Tokenization for Hindi , English, Math & Code
 * Tied Embeddings
 * Torch-XLA (SPMD)
 * Flash-Attention ( Block-Size = 512 )
@@ -52,5 +53,4 @@ Evals will be in [Dir](https://huggingface.co/tinycompany/BiBo-Mini-1.7B-SFT-Sta
 
 Compute Provided by [Google](https://huggingface.co/google)  ;)
 
-
 ❤️ TRC ❤️Google