Update app.py

app.py

@@ -32,10 +32,10 @@ import torch
 
 # Create a configuration for quantization
 quantization_config = BitsAndBytesConfig(
-    load_in_8bit=True,   
-    bnb_8bit_compute_dtype="float16",  
-    bnb_8bit_use_double_quant=True,    
-    bnb_8bit_quant_type="nf4",         
+    load_in_4bit=True,   
+    bnb_4bit_compute_dtype="float16",  
+    bnb_4bit_use_double_quant=True,    
+    bnb_4bit_quant_type="nf4",         
 )
 
 # Load the model and processor