Update README.md

README.md

@@ -113,6 +113,7 @@ We evaluated the models on the following datasets:
 #### Evaluation on English Benchmark datasets
 - **gemma-2-2b** outperforms **titulm-gemma-2-2b-v1.0** across all tasks in both 0-shot and 5-shot settings, achieving the highest scores in **MMLU**, **BoolQ**, **Commonsense QA**, **OpenBook QA**, and **PIQA**, with a peak 5-shot score of **0.80** in **PIQA**.
 - **titulm-gemma-2-2b-v1.0** shows competitive performance but lags behind **gemma-2-2b**, particularly in **Commonsense QA** and **BoolQ**, with the highest score being **0.77** in **PIQA**.
+- It is expected as we have trained our model only on Bangla text.
 
 | Model                                | Shots  | MMLU         | BoolQ      | Commonsense QA     | OpenBook QA     | PIQA      |
 |--------------------------------------|--------|--------------|------------|--------------------|-----------------|-----------|