Diff converter v2

src/transformers/models/gemma/configuration_gemma.py

@@ -1,5 +1,6 @@
 # coding=utf-8
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
+# Copyright 2024 Google Inc. HuggingFace Inc. team. All rights reserved.
+#
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -12,27 +13,20 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-"""Gemma model configuration"""
 
-from ...configuration_utils import PretrainedConfig
-from ...utils import logging
 
 
-logger = logging.get_logger(__name__)
+from transformers import PretrainedConfig
 
 
 class GemmaConfig(PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`GemmaModel`]. It is used to instantiate an Gemma
     model according to the specified arguments, defining the model architecture. Instantiating a configuration with the
     defaults will yield a similar configuration to that of the Gemma-7B.
-
     e.g. [google/gemma-7b](https://huggingface.co/google/gemma-7b)
-
     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 256000):
             Vocabulary size of the Gemma model. Defines the number of different tokens that can be represented by the
@@ -83,20 +77,15 @@ class GemmaConfig(PretrainedConfig):
             Whether to use a bias in the query, key, value and output projection layers during self-attention.
         attention_dropout (`float`, *optional*, defaults to 0.0):
             The dropout ratio for the attention probabilities.
-
     ```python
     >>> from transformers import GemmaModel, GemmaConfig
-
     >>> # Initializing a Gemma gemma-7b style configuration
     >>> configuration = GemmaConfig()
-
     >>> # Initializing a model from the gemma-7b style configuration
     >>> model = GemmaModel(configuration)
-
     >>> # Accessing the model configuration
     >>> configuration = model.config
     ```"""
-
     model_type = "gemma"
     keys_to_ignore_at_inference = ["past_key_values"]