Update app.py

app.py

@@ -172,7 +172,7 @@ def test(base_model_id, dataset):
     model_kwargs = dict(
         use_cache=False,
         trust_remote_code=True,
-        attn_implementation="flash_attention_2",  # loading the model with flash-attenstion support
+        #attn_implementation="flash_attention_2",  # loading the model with flash-attenstion support
         torch_dtype=torch.bfloat16,
         device_map=None
     )