Update app.py

app.py

@@ -40,6 +40,7 @@ def initialize_system():
     # Quantization config
     bnb_config = BitsAndBytesConfig(
         load_in_4bit=True,
+        bnb_4bit_use_double_quant=True,
         bnb_4bit_quant_type="nf4",
         bnb_4bit_compute_dtype=torch.float16,
     )
@@ -50,7 +51,8 @@ def initialize_system():
         MODEL_NAME,
         quantization_config=bnb_config,
         device_map="auto",
-        trust_remote_code=True
+        trust_remote_code=True,
+        use_flash_attention_2=True 
     )
     
     return vector_store, model, tokenizer