Update modeling_nandi.py

modeling_nandi.py

@@ -23,20 +23,20 @@ from collections.abc import Callable
 import torch
 import torch.nn as nn
 
-from ...activations import ACT2FN
-from ...cache_utils import Cache, DynamicCache, DynamicLayer
-from ...generation import GenerationMixin
-from ...integrations import use_kernel_forward_from_hub
-from ...masking_utils import create_causal_mask
-from ...modeling_layers import GradientCheckpointingLayer
-from ...modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
-from ...modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
-from ...modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
-from ...processing_utils import Unpack
-from ...utils import TransformersKwargs, auto_docstring
-from ...utils.deprecation import deprecate_kwarg
-from ...utils.generic import can_return_tuple, merge_with_config_defaults
-from ...utils.output_capturing import capture_outputs
+from transformers.activations import ACT2FN
+from transformers.cache_utils import Cache, DynamicCache, DynamicLayer
+from transformers.generation import GenerationMixin
+from transformers.integrations import use_kernel_forward_from_hub
+from transformers.masking_utils import create_causal_mask
+from transformers.modeling_layers import GradientCheckpointingLayer
+from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
+from transformers.modeling_rope_utils import ROPE_INIT_FUNCTIONS, dynamic_rope_update
+from transformers.modeling_utils import ALL_ATTENTION_FUNCTIONS, PreTrainedModel
+from transformers.processing_utils import Unpack
+from transformers.utils import TransformersKwargs, auto_docstring
+from transformers.utils.deprecation import deprecate_kwarg
+from transformers.utils.generic import can_return_tuple, merge_with_config_defaults
+from transformers.utils.output_capturing import capture_outputs
 from .configuration_nandi import NandiConfig
 
 
@@ -109,8 +109,8 @@ class NandiRotaryEmbedding(nn.Module):
 
 def rotate_half(x):
     """Rotates half the hidden dims of the input."""
-    x1 = x[..., : x.shape[-1] // 2]
-    x2 = x[..., x.shape[-1] // 2 :]
+    x1 = x[transformers., : x.shape[-1] // 2]
+    x2 = x[transformers., x.shape[-1] // 2 :]
     return torch.cat((-x2, x1), dim=-1)