From 51042ae8e5df8275d16b3eaff36c20fb9c191655 Mon Sep 17 00:00:00 2001 From: louietouie <80791777+louietouie@users.noreply.github.com> Date: Tue, 17 Oct 2023 13:30:46 -0400 Subject: [PATCH] [docstring] Fix docstring for LukeConfig (#26858) * Deleted LukeConfig and ran check_docstrings.py * Filled docstring information --------- Co-authored-by: louie --- src/transformers/models/luke/configuration_luke.py | 10 ++++++++-- utils/check_docstrings.py | 1 - 2 files changed, 8 insertions(+), 3 deletions(-) diff --git a/src/transformers/models/luke/configuration_luke.py b/src/transformers/models/luke/configuration_luke.py index 6e5c99900bb..099a5cf6d9b 100644 --- a/src/transformers/models/luke/configuration_luke.py +++ b/src/transformers/models/luke/configuration_luke.py @@ -38,7 +38,7 @@ class LukeConfig(PretrainedConfig): Args: - vocab_size (`int`, *optional*, defaults to 30522): + vocab_size (`int`, *optional*, defaults to 50267): Vocabulary size of the LUKE model. Defines the number of different tokens that can be represented by the `inputs_ids` passed when calling [`LukeModel`]. entity_vocab_size (`int`, *optional*, defaults to 500000): @@ -70,12 +70,18 @@ class LukeConfig(PretrainedConfig): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. layer_norm_eps (`float`, *optional*, defaults to 1e-12): The epsilon used by the layer normalization layers. - use_entity_aware_attention (`bool`, defaults to `True`): + use_entity_aware_attention (`bool`, *optional*, defaults to `True`): Whether or not the model should use the entity-aware self-attention mechanism proposed in [LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention (Yamada et al.)](https://arxiv.org/abs/2010.01057). classifier_dropout (`float`, *optional*): The dropout ratio for the classification head. + pad_token_id (`int`, *optional*, defaults to 1): + Padding token id. + bos_token_id (`int`, *optional*, defaults to 0): + Beginning of stream token id. + eos_token_id (`int`, *optional*, defaults to 2): + End of stream token id. Examples: diff --git a/utils/check_docstrings.py b/utils/check_docstrings.py index f46ad8995c3..67a89193d4c 100644 --- a/utils/check_docstrings.py +++ b/utils/check_docstrings.py @@ -356,7 +356,6 @@ OBJECTS_TO_IGNORE = [ "LongformerConfig", "LongformerModel", "LongformerTokenizerFast", - "LukeConfig", "LukeModel", "LukeTokenizer", "LxmertTokenizerFast",