Update app.py

app.py

@@ -14,7 +14,7 @@ Model ID: {MODEL_ID}
 🚀 **Experience the power of LLM mathematical reasoning** through [our Llama 2 sparse finetuned](https://arxiv.org/abs/2310.06927) on the [GSM8K dataset](https://huggingface.co/datasets/gsm8k). 
 GSM8K, short for Grade School Math 8K, is a collection of 8.5K high-quality linguistically diverse grade school math word problems, designed to challenge question-answering systems with multi-step reasoning. 
 Observe the model's performance in deciphering complex math questions and offering detailed step-by-step solutions.
-## Accelerated Inferenced on CPUs 
+## Accelerated Inference on CPUs 
 The Llama 2 model runs purely on CPU courtesy of [sparse software execution by DeepSparse](https://github.com/neuralmagic/deepsparse/tree/main/research/mpt). 
 DeepSparse provides accelerated inference by taking advantage of the model's weight sparsity to deliver tokens fast!