Update model.py

model.py

@@ -16,7 +16,7 @@ from transformers.activations import ACT2FN
 from transformers.modeling_attn_mask_utils import AttentionMaskConverter, _prepare_4d_causal_attention_mask
 from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, SequenceClassifierOutputWithPast
 from transformers.modeling_utils import PreTrainedModel
-from transformers.pytorch_utils import ALL_LAYERNORM_LAYERS, is_torch_greater_or_equal_than_1_13
+from transformers.pytorch_utils import ALL_LAYERNORM_LAYERS
 from transformers.utils import (
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
@@ -36,8 +36,8 @@ if is_flash_attn_2_available():
 # This makes `_prepare_4d_causal_attention_mask` a leaf function in the FX graph.
 # It means that the function will not be traced through and simply appear as a node in the graph.
 if is_torch_fx_available():
-    if not is_torch_greater_or_equal_than_1_13:
-        import torch.fx
+
+    import torch.fx
 
     _prepare_4d_causal_attention_mask = torch.fx.wrap(_prepare_4d_causal_attention_mask)