Update modeling_moe_mistral.py

modeling_moe_mistral.py

@@ -29,12 +29,12 @@ 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
-from ...modeling_attn_mask_utils import _prepare_4d_causal_attention_mask
-from ...modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, SequenceClassifierOutputWithPast
-from ...modeling_utils import PreTrainedModel
-from ...utils import (
+from transformers.activations import ACT2FN
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.modeling_attn_mask_utils import _prepare_4d_causal_attention_mask
+from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast, SequenceClassifierOutputWithPast
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import (
     add_start_docstrings,
     add_start_docstrings_to_model_forward,
     is_flash_attn_2_available,
@@ -42,7 +42,7 @@ from ...utils import (
     logging,
     replace_return_docstrings,
 )
-from .configuration_dmoe_mistral import MixtralConfig
+from .configuration_moe_mistral import MixtralConfig