Update app.py

app.py

@@ -115,8 +115,8 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
-    quantization_config=quantization_config,
-    attn_implementation="flash_attention_2",
+    #quantization_config=quantization_config,
+    #attn_implementation="flash_attention_2",
 )
 
 # Create Gradio interface