Update README.md

README.md

@@ -12,7 +12,7 @@ widget:
     content: What is your favorite condiment?
 ---
 
-This model is compressed from the Mixtral-8x7B model. Using Low-Rank Approximation, I removed 10 billion parameters from the MLP experts' matrices, enough to run the model on a single A100 80GB GPU using half precision. 
+This model is compressed from the Mixtral-8x7B. Using Low-Rank Approximation, I removed 10 billion parameters from the MLP experts' matrices, enough to run the model on a single A100 80GB GPU using half precision. 
 
 
 The model still retains its core performance: