Update app.py

app.py

@@ -62,7 +62,7 @@ model = AutoModelForCausalLM.from_pretrained(model_id, token= token,
                                              # torch_dtype=torch.float16,
                                              #  load_in_8bit=True,
                                              #  # torch_dtype=torch.fl,
-                                             attn_implementation="flash_attention_2",
+                                             # attn_implementation="flash_attention_2",
                                              # low_cpu_mem_usage=True,
                                              # device_map='cuda',
                                              # device_map=accelerator.device_map,