fastNLP/fastNLP/transformers/torch/models/bart/configuration_bart.py

# coding=utf-8
# Copyright 2021 The Fairseq Authors 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
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# 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.
""" BART model configuration """
from fastNLP.transformers.torch.configuration_utils import PretrainedConfig
from fastNLP.core.log import logger

__all__ = [
    "BartConfig",
    "BART_PRETRAINED_CONFIG_ARCHIVE_MAP",
]

BART_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    "facebook/bart-large": "https://huggingface.co/facebook/bart-large/resolve/main/config.json",
    # See all BART models at https://huggingface.co/models?filter=bart
}


class BartConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a :class:`~transformers.BartModel`. It is used to
    instantiate a BART 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 BART `facebook/bart-large
    <https://huggingface.co/facebook/bart-large>`__ 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 BART model. Defines the number of different tokens that can be represented by the
            :obj:`inputs_ids` passed when calling :class:`~transformers.BartModel` or
            :class:`~transformers.TFBartModel`.
        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_position_embeddings (:obj:`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).
        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
            https://arxiv.org/abs/1909.11556>`__ for more details.
        decoder_layerdrop: (:obj:`float`, `optional`, defaults to 0.0):
            The LayerDrop probability for the decoder. See the `LayerDrop paper <see
            https://arxiv.org/abs/1909.11556>`__ for more details.
        scale_embedding (:obj:`bool`, `optional`, defaults to :obj:`False`):
            Scale embeddings by diving by sqrt(d_model).
        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).
        num_labels: (:obj:`int`, `optional`, defaults to 3):
            The number of labels to use in :class:`~transformers.BartForSequenceClassification`.
        forced_eos_token_id (:obj:`int`, `optional`, defaults to 2):
            The id of the token to force as the last generated token when :obj:`max_length` is reached. Usually set to
            :obj:`eos_token_id`.

    Example::

        >>> from transformers import BartModel, BartConfig

        >>> # Initializing a BART facebook/bart-large style configuration
        >>> configuration = BartConfig()

        >>> # Initializing a model from the facebook/bart-large style configuration
        >>> model = BartModel(configuration)

        >>> # Accessing the model configuration
        >>> configuration = model.config
    """
    model_type = "bart"
    keys_to_ignore_at_inference = ["past_key_values"]
    attribute_map = {"num_attention_heads": "encoder_attention_heads", "hidden_size": "d_model"}

    def __init__(
        self,
        vocab_size=50265,
        max_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,
        activation_function="gelu",
        d_model=1024,
        dropout=0.1,
        attention_dropout=0.0,
        activation_dropout=0.0,
        init_std=0.02,
        classifier_dropout=0.0,
        scale_embedding=False,
        use_cache=True,
        num_labels=3,
        pad_token_id=1,
        bos_token_id=0,
        eos_token_id=2,
        is_encoder_decoder=True,
        decoder_start_token_id=2,
        forced_eos_token_id=2,
        **kwargs
    ):
        self.vocab_size = vocab_size
        self.max_position_embeddings = max_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.scale_embedding = scale_embedding  # scale factor will be sqrt(d_model) if True

        super().__init__(
            num_labels=num_labels,
            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,
            forced_eos_token_id=forced_eos_token_id,
            **kwargs,
        )

        # ensure backward compatibility for BART CNN models
        if self.forced_bos_token_id is None and kwargs.get("force_bos_token_to_be_generated", False):
            self.forced_bos_token_id = self.bos_token_id
            logger.rank_zero_warning(
                f"Please make sure the config includes `forced_bos_token_id={self.bos_token_id}` in future versions."
                "The config can simply be saved and uploaded again to be fixed."
            )