Update modeling_gemmoe.py

modeling_gemmoe.py

@@ -25,15 +25,15 @@ import torch.utils.checkpoint
 from torch import nn
 from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
 
-from ...activations import ACT2FN
-from ...cache_utils import Cache, DynamicCache, StaticCache
-from ...modeling_attn_mask_utils import (
+from transformers.activations import ACT2FN
+from transformers.cache_utils import Cache, DynamicCache, StaticCache
+from transformers.modeling_attn_mask_utils import (
     _prepare_4d_causal_attention_mask,
 )
-from ...modeling_outputs import SequenceClassifierOutputWithPast, MoeModelOutputWithPast, MoeCausalLMOutputWithPast
-from ...modeling_utils import PreTrainedModel
-from ...pytorch_utils import ALL_LAYERNORM_LAYERS, is_torch_greater_or_equal_than_1_13
-from ...utils import (
+from transformers.modeling_outputs import SequenceClassifierOutputWithPast, MoeModelOutputWithPast, MoeCausalLMOutputWithPast
+from transformers.modeling_utils import PreTrainedModel
+from transformers.pytorch_utils import ALL_LAYERNORM_LAYERS, is_torch_greater_or_equal_than_1_13
+from transformers.utils import (
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
     is_flash_attn_2_available,
@@ -41,7 +41,7 @@ from ...utils import (
     logging,
     replace_return_docstrings,
 )
-from ...utils.import_utils import is_torch_fx_available
+from transformers.utils.import_utils import is_torch_fx_available
 from .configuration_gemmoe import GemmoeConfig
 
 from math import sqrt as math_sqrt