Update app.py

app.py

@@ -81,8 +81,8 @@ def initialize_model():
         MODEL_ID,
         torch_dtype=torch.float16,
         device_map="cuda",
-        attn_implementation="flash_attention_2",
-        quantization_config=quantization_config
+        # attn_implementation="flash_attention_2",
+        # quantization_config=quantization_config
 
     )
 
@@ -133,7 +133,7 @@ def create_examples():
         "What is the role of DNA in genetics?"
     ]
 
-@spaces.GPU(duration=120)
+@spaces.GPU
 def chat_response(
     message: str,
     history: list,