Update README.md

README.md

@@ -2,7 +2,7 @@
 language:
 - en
 license: apache-2.0
-base_model: mistralai/Mixtral-8x7B-v0.1
+base_model: mistralai/Mixtral-8x7B-v0.1-Instruct
 inference:
   parameters:
     temperature: 0.5
@@ -12,7 +12,7 @@ widget:
     content: What is your favorite condiment?
 ---
 
-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. 
+This model is compressed from the Mixtral-8x7B-Instruct. 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. 
 
 
 Without being retrained or fine-tuned, the model still retains its core performance: