Update app.py

app.py

@@ -36,7 +36,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                              device_map="auto",
                                              trust_remote_code=True,
                                              revision="main",
-                                             #quantization_config=QuantizationConfig(disable_exllama=True)
+                                             quantization_config=QuantizationConfig(disable_exllama=True)
                                              )
 
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)