Update configuration_codeshell.py

configuration_codeshell.py

@@ -17,7 +17,6 @@
 # its original forms to accommodate minor architectural differences compared to 
 # GPTBigCode Configuration that trained the model.
 
-# coding=utf-8
 # Copyright 2023 The BigCode team and HuggingFace Inc. team.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -31,7 +30,7 @@
 # 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.
-""" CodeShell configuration"""
+""" Shell configuration"""
 
 from transformers.configuration_utils import PretrainedConfig
 from transformers.utils import logging
@@ -51,7 +50,7 @@ class CodeShellConfig(PretrainedConfig):
     Args:
         vocab_size (`int`, *optional*, defaults to 50257):
             Vocabulary size of the GPT-2 model. Defines the number of different tokens that can be represented by the
-            `inputs_ids` passed when calling [`CodeShellModel`].
+            `inputs_ids` passed when calling [`ShellModel`].
         n_positions (`int`, *optional*, defaults to 1024):
             The maximum sequence length that this model might ever be used with. Typically set this to something large
             just in case (e.g., 512 or 1024 or 2048).
@@ -86,7 +85,21 @@ class CodeShellConfig(PretrainedConfig):
             Whether to scale the attention softmax in float32.
         attention_type (`bool`, *optional*, defaults to `True`):
             Whether to use Multi-Query Attion (`True`) or Multi-Head Attention (`False`).
-    """
+    Example:
+
+    ```python
+    >>> from configuration_codeshell import CodeShellConfig
+    >>> from modeling_codeshell import CodeShellForCausalLM
+
+    >>> # Initializing a CodeShell configuration
+    >>> configuration = CodeShellConfig()
+
+    >>> # Initializing a model (with random weights) from the configuration
+    >>> model = CodeShellForCausalLM(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+    ```"""
 
     model_type = "codeshell"
     keys_to_ignore_at_inference = ["past_key_values"]