Update app.py

app.py

@@ -39,8 +39,8 @@ tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
     device_map="auto",
-    torch_dtype=torch.bfloat16,
-    attn_implementation="flash_attention_2",
+    # torch_dtype=torch.bfloat16,
+    # attn_implementation="flash_attention_2",
     quantization_config=quantization_config,
 )
 model.eval()