fengshen/models/roformer/configuration_roformer.py

# coding=utf-8
# Copyright 2021 The IDEA Authors. 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.
""" RoFormer model configuration """


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


logger = logging.get_logger(__name__)

RoFormer_PRETRAINED_CONFIG_ARCHIVE_MAP = {
    # See all RoFormer models at https://huggingface.co/models?filter=bert
}


class RoFormerConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a :class:`~transformers.RoFormerModel`. It is
    used to instantiate a RoFormer 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 RoFormer
    `megatron-bert-uncased-345m <https://huggingface.co/nvidia/megatron-bert-uncased-345m>`__ 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 29056):
            Vocabulary size of the RoFormer model. Defines the number of different tokens that can be represented
            by the :obj:`inputs_ids` passed when calling :class:`~transformers.RoFormerModel`.
        hidden_size (:obj:`int`, `optional`, defaults to 1024):
            Dimensionality of the encoder layers and the pooler layer.
        num_hidden_layers (:obj:`int`, `optional`, defaults to 24):
            Number of hidden layers in the Transformer encoder.
        num_attention_heads (:obj:`int`, `optional`, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        intermediate_size (:obj:`int`, `optional`, defaults to 4096):
            Dimensionality of the "intermediate" (often named feed-forward) layer in the Transformer encoder.
        hidden_act (:obj:`str` or :obj:`Callable`, `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.
        hidden_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_probs_dropout_prob (:obj:`float`, `optional`, defaults to 0.1):
            The dropout ratio for the attention probabilities.
        max_position_embeddings (:obj:`int`, `optional`, defaults to 512):
            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).
        type_vocab_size (:obj:`int`, `optional`, defaults to 2):
            The vocabulary size of the :obj:`token_type_ids` passed when calling
            :class:`~transformers.RoFormerModel`.
        initializer_range (:obj:`float`, `optional`, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        layer_norm_eps (:obj:`float`, `optional`, defaults to 1e-12):
            The epsilon used by the layer normalization layers.
        gradient_checkpointing (:obj:`bool`, `optional`, defaults to :obj:`False`):
            If True, use gradient checkpointing to save memory at the expense of slower backward pass.
        position_embedding_type (:obj:`str`, `optional`, defaults to :obj:`"absolute"`):
            Type of position embedding. Choose one of :obj:`"absolute"`, :obj:`"relative_key"`,
            :obj:`"relative_key_query"`. For positional embeddings use :obj:`"absolute"`. For more information on
            :obj:`"relative_key"`, please refer to `Self-Attention with Relative Position Representations (Shaw et al.)
            <https://arxiv.org/abs/1803.02155>`__. For more information on :obj:`"relative_key_query"`, please refer to
            `Method 4` in `Improve Transformer Models with Better Relative Position Embeddings (Huang et al.)
            <https://arxiv.org/abs/2009.13658>`__.
        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). Only
            relevant if ``config.is_decoder=True``.

    Examples::

        >>> from transformers import RoFormerModel, RoFormerConfig

        >>> # Initializing a RoFormer bert-base-uncased style configuration
        >>> configuration = RoFormerConfig()

        >>> # Initializing a model from the bert-base-uncased style configuration
        >>> model = RoFormerModel(configuration)

        >>> # Accessing the model configuration
        >>> configuration = model.config
    """
    model_type = "roformer"

    def __init__(
        self,
        vocab_size=29056,
        hidden_size=1024,
        num_hidden_layers=24,
        num_attention_heads=16,
        intermediate_size=4096,
        hidden_act="gelu",
        hidden_dropout_prob=0.1,
        attention_probs_dropout_prob=0.1,
        max_position_embeddings=512,
        type_vocab_size=2,
        initializer_range=0.02,
        layer_norm_eps=1e-12,
        pad_token_id=0,
        gradient_checkpointing=False,
        position_embedding_type="absolute",
        use_cache=True,
        **kwargs
    ):
        super().__init__(pad_token_id=pad_token_id, **kwargs)

        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.gradient_checkpointing = gradient_checkpointing
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache