Update configuration_motif.py

configuration_motif.py

@@ -1,8 +1,9 @@
+import math
+from typing import Optional
+
 from transformers.configuration_utils import PretrainedConfig
 from transformers.modeling_rope_utils import rope_config_validation
 from transformers.utils import logging
-from typing import Optional
-import math
 
 logger = logging.get_logger(__name__)
 
@@ -13,11 +14,8 @@ class MotifConfig(PretrainedConfig):
     Motif model according to the specified arguments, defining the model architecture. Instantiating a configuration
     with the defaults will yield a similar configuration to that of
     Motif-102B [moreh/Motif-102B](https://huggingface.co/moreh/Motif-102B).
-
     Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
     documentation from [`PretrainedConfig`] for more information.
-
-
     Args:
         vocab_size (`int`, *optional*, defaults to 151936):
             Vocabulary size of the Motif model. Defines the number of different tokens that can be represented by the
@@ -97,16 +95,12 @@ class MotifConfig(PretrainedConfig):
             The number of layers that use SWA (Sliding Window Attention). The bottom layers use SWA while the top use full attention.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
-
     ```python
     >>> from transformers import MotifModel, MotifConfig
-
     >>> # Initializing a Motif style configuration
     >>> configuration = MotifConfig()
-
     >>> # Initializing a model from the Motif-102B style configuration
     >>> model = MotifModel(configuration)
-
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
@@ -170,4 +164,4 @@ class MotifConfig(PretrainedConfig):
             tie_word_embeddings=tie_word_embeddings,
             **kwargs,
         )
-        logger.info(f' kwargs : {kwargs}')
+        logger.info(f' kwargs : {kwargs}')