Update README.md

README.md

@@ -45,7 +45,7 @@ Our final vocab file availabe at [https://github.com/sagorbrur/bangla-bert](http
 * Bangla-Bert was trained with code provided in Google BERT's github repository (https://github.com/google-research/bert)
 * Currently released model follows bert-base-uncased model architecture (12-layer, 768-hidden, 12-heads, 110M parameters)
 * Total Training Steps: 1 Million
-* The model was trained on a single Google Cloud TPU 
+* The model was trained on a single Google Cloud GPU
 
 ## Evaluation Results
 
@@ -142,6 +142,11 @@ for pred in nlp(f"আমি বাংলায় {nlp.tokenizer.mask_token} গা
 ## Reference
 * https://github.com/google-research/bert
 
+## Acknowledgements
+
+* Thanks to Google [TensorFlow Research Cloud (TFRC)](https://www.tensorflow.org/tfrc) for providing the free GPU credits - thank you!
+* Thank to all the people around, who always helping us to build something for Bengali.
+
 ## Citation
 If you find this model helpful, please cite.