Update README.md

README.md

@@ -37,7 +37,7 @@ Replace `{instruction}`, `{input}` and `{output}` with your desired Telugu text.
 
 This model didn't skip leg day! It was finetuned on the telugu_teknium_GPTeacher_general_instruct_filtered_romanized dataset containing a whopping 43,614 examples of Telugu instructions and outputs. 💪
 
-But how did we make training lightning fast? By using Unsloth and the TRL library from Huggingface, enabling 2x faster training! ⚡ We also added LoRA adapters for efficient finetuning of the 7B parameter model and used mixed precision training with bfloat16. 
+But how was the training done lightning fast? By using Unsloth and the TRL library from Huggingface, enabling 2x faster training! ⚡ Also added LoRA adapters for efficient finetuning of the 7B parameter model and used mixed precision training with bfloat16. 
 
 And the best part? Unsloth provides optimized inference code to run the model 2x faster. Talk about having your cake and eating it too! 🍰