Update README.md

README.md

@@ -215,9 +215,9 @@ Gemma-3n utilizes a Matryoshka Transformer (MatFormer) architecture, which nests
 
 ## 🙏 Acknowledgements
 This work would not have been possible without the foundational models and libraries developed by the open-source community. We would like to extend our gratitude to:
--Google: For developing and releasing the powerful gemma-3n-E2B-it base model.
--The Unsloth AI team: For creating the Unsloth library, which was instrumental in accelerating the training process and reducing computational costs.
--Hugging Face: For providing the transformers, datasets, and TRL libraries that formed the backbone of our training and experimentation pipeline.
+- Google: For developing and releasing the powerful gemma-3n-E2B-it base model.
+- The Unsloth AI team: For creating the Unsloth library, which was instrumental in accelerating the training process and reducing computational costs.
+- Hugging Face: For providing the transformers, datasets, and TRL libraries that formed the backbone of our training and experimentation pipeline.
 
 ## 📖 Citation