Source code for transformers.models.led.configuration_led

# coding=utf-8
# Copyright 2021 Iz Beltagy, Matthew E. Peters, Arman Cohan and The 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.
# You may obtain a copy of the License at
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.
""" LED model configuration """

from typing import List, Union

from ...configuration_utils import PretrainedConfig
from ...utils import logging

logger = logging.get_logger(__name__)

    "allenai/led-base-16384": "",
    # See all LED models at

[docs]class LEDConfig(PretrainedConfig): r""" This is the configuration class to store the configuration of a :class:`~transformers.LEDModel`. It is used to instantiate an LED 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 LED `allenai/led-base-16384 <>`__ architecture. Configuration objects inherit from :class:`~transformers.PretrainedConfig` and can be used to control the model outputs. Read the documentation from :class:`~transformers.PretrainedConfig` for more information. Args: vocab_size (:obj:`int`, `optional`, defaults to 50265): Vocabulary size of the LED model. Defines the number of different tokens that can be represented by the :obj:`inputs_ids` passed when calling :class:`~transformers.LEDModel` or :class:`~transformers.TFLEDModel`. d_model (:obj:`int`, `optional`, defaults to 1024): Dimensionality of the layers and the pooler layer. encoder_layers (:obj:`int`, `optional`, defaults to 12): Number of encoder layers. decoder_layers (:obj:`int`, `optional`, defaults to 12): Number of decoder layers. encoder_attention_heads (:obj:`int`, `optional`, defaults to 16): Number of attention heads for each attention layer in the Transformer encoder. decoder_attention_heads (:obj:`int`, `optional`, defaults to 16): Number of attention heads for each attention layer in the Transformer decoder. decoder_ffn_dim (:obj:`int`, `optional`, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. encoder_ffn_dim (:obj:`int`, `optional`, defaults to 4096): Dimensionality of the "intermediate" (often named feed-forward) layer in decoder. activation_function (:obj:`str` or :obj:`function`, `optional`, defaults to :obj:`"gelu"`): The non-linear activation function (function or string) in the encoder and pooler. If string, :obj:`"gelu"`, :obj:`"relu"`, :obj:`"silu"` and :obj:`"gelu_new"` are supported. dropout (:obj:`float`, `optional`, defaults to 0.1): The dropout probability for all fully connected layers in the embeddings, encoder, and pooler. attention_dropout (:obj:`float`, `optional`, defaults to 0.0): The dropout ratio for the attention probabilities. activation_dropout (:obj:`float`, `optional`, defaults to 0.0): The dropout ratio for activations inside the fully connected layer. classifier_dropout (:obj:`float`, `optional`, defaults to 0.0): The dropout ratio for classifier. max_encoder_position_embeddings (:obj:`int`, `optional`, defaults to 16384): The maximum sequence length that the encoder might ever be used with. max_decoder_position_embeddings (:obj:`int`, `optional`, defaults to 16384): The maximum sequence length that the decoder might ever be used with. init_std (:obj:`float`, `optional`, defaults to 0.02): The standard deviation of the truncated_normal_initializer for initializing all weight matrices. encoder_layerdrop: (:obj:`float`, `optional`, defaults to 0.0): The LayerDrop probability for the encoder. See the `LayerDrop paper <see>`__ for more details. decoder_layerdrop: (:obj:`float`, `optional`, defaults to 0.0): The LayerDrop probability for the decoder. See the `LayerDrop paper <see>`__ for more details. use_cache (:obj:`bool`, `optional`, defaults to :obj:`True`): Whether or not the model should return the last key/values attentions (not used by all models) gradient_checkpointing (:obj:`bool`, `optional`, defaults to :obj:`False`): If True, use gradient checkpointing to save memory at the expense of slower backward pass. Example:: >>> from transformers import LEDModel, LEDConfig >>> # Initializing a LED allenai/led-base-16384 style configuration >>> configuration = LEDConfig() >>> # Initializing a model from the allenai/led-base-16384 style configuration >>> model = LEDModel(configuration) >>> # Accessing the model configuration >>> configuration = model.config """ model_type = "led" def __init__( self, vocab_size=50265, max_encoder_position_embeddings=16384, max_decoder_position_embeddings=1024, encoder_layers=12, encoder_ffn_dim=4096, encoder_attention_heads=16, decoder_layers=12, decoder_ffn_dim=4096, decoder_attention_heads=16, encoder_layerdrop=0.0, decoder_layerdrop=0.0, use_cache=True, is_encoder_decoder=True, activation_function="gelu", d_model=1024, dropout=0.1, attention_dropout=0.0, activation_dropout=0.0, init_std=0.02, decoder_start_token_id=2, classifier_dropout=0.0, pad_token_id=1, bos_token_id=0, eos_token_id=2, gradient_checkpointing=False, attention_window: Union[List[int], int] = 512, **kwargs ): super().__init__( pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, is_encoder_decoder=is_encoder_decoder, decoder_start_token_id=decoder_start_token_id, **kwargs, ) self.vocab_size = vocab_size self.max_encoder_position_embeddings = max_encoder_position_embeddings self.max_decoder_position_embeddings = max_decoder_position_embeddings self.d_model = d_model self.encoder_ffn_dim = encoder_ffn_dim self.encoder_layers = encoder_layers self.encoder_attention_heads = encoder_attention_heads self.decoder_ffn_dim = decoder_ffn_dim self.decoder_layers = decoder_layers self.decoder_attention_heads = decoder_attention_heads self.dropout = dropout self.attention_dropout = attention_dropout self.activation_dropout = activation_dropout self.activation_function = activation_function self.init_std = init_std self.encoder_layerdrop = encoder_layerdrop self.decoder_layerdrop = decoder_layerdrop self.classifier_dropout = classifier_dropout self.use_cache = use_cache self.num_hidden_layers = encoder_layers self.attention_window = attention_window self.gradient_checkpointing = gradient_checkpointing @property def num_attention_heads(self) -> int: return self.encoder_attention_heads @property def hidden_size(self) -> int: return self.d_model @property def attention_probs_dropout_prob(self) -> float: return self.attention_dropout @property def initializer_range(self) -> float: return self.init_std