Update app.py

app.py

@@ -17,7 +17,7 @@ client = InferenceClient(token=HF_API_KEY)
 
 
 # ✅ Load Local Model with Device Optimization
-MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.3"
+MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.2" 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)