Update app.py

app.py

@@ -34,7 +34,8 @@ def mistral_model():
         print("CUDA is not available. CPU will be used.")
    
     tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
-    model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
+    model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2/model-00001-of-00003.safetensors
+")
 
     return model,tokenizer