Update app.py

app.py

@@ -17,7 +17,9 @@ dtype = None  # Auto detection of dtype
 load_in_4bit = True  # Use 4-bit quantization to reduce memory usage
 
 # peft_model_name = "limitedonly41/website_qwen2_7b_2"
-peft_model_name = "limitedonly41/website_mistral7b_v02"
+# peft_model_name = "limitedonly41/website_mistral7b_v02"
+peft_model_name = "unsloth/mistral-7b-instruct-v0.3-bnb-4bit"
+
 # Initialize model and tokenizer variables
 model = None
 tokenizer = None