Update README.md

README.md

@@ -33,7 +33,7 @@ Varying from the original paper, this model is a fine-tuned version of [meta-lla
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 The dataset used to train this model is a combination of data sampled from the [oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) 
-dataset and the synthetic dataset which was mentioned above. Latter has been created by applying self-augmentation and self-curation 
+dataset and the synthetic dataset which was mentioned above. The latter has been created by applying self-augmentation and self-curation 
 on 502k entries from the english subset ("en") of the [c4](https://huggingface.co/datasets/allenai/c4) dataset.
 
 ### Framework versions