configuration_deltalm.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

""" deltalm model configuration"""

import warnings
from transformers.configuration_utils import PretrainedConfig
from transformers.utils import logging
logger = logging.get_logger(__name__)

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


class DeltalmConfig(PretrainedConfig):
    r"""
    This is the configuration class to store the configuration of a [`DeltalmModel`]. It is used to instantiate a Deltalm
    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 [`PretrainedConfig`] and can be used to control the model outputs. Read the
    documentation from [`PretrainedConfig`] for more information.
    Args:
        vocab_size (`int`, *optional*, defaults to 50265):
            Vocabulary size of the BART model. Defines the number of different tokens that can be represented by the
            `inputs_ids` passed when calling [`BartModel`] or [`TFBartModel`].
        d_model (`int`, *optional*, defaults to 1024):
            Dimensionality of the layers and the pooler layer.
        encoder_layers (`int`, *optional*, defaults to 12):
            Number of encoder layers.
        decoder_layers (`int`, *optional*, defaults to 12):
            Number of decoder layers.
        encoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer encoder.
        decoder_attention_heads (`int`, *optional*, defaults to 16):
            Number of attention heads for each attention layer in the Transformer decoder.
        decoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
        encoder_ffn_dim (`int`, *optional*, defaults to 4096):
            Dimensionality of the "intermediate" (often named feed-forward) layer in decoder.
        activation_function (`str` or `function`, *optional*, defaults to `"gelu"`):
            The non-linear activation function (function or string) in the encoder and pooler. If string, `"gelu"`,
            `"relu"`, `"silu"` and `"gelu_new"` are supported.
        dropout (`float`, *optional*, defaults to 0.1):
            The dropout probability for all fully connected layers in the embeddings, encoder, and pooler.
        attention_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for the attention probabilities.
        activation_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for activations inside the fully connected layer.
        classifier_dropout (`float`, *optional*, defaults to 0.0):
            The dropout ratio for classifier.
        max_position_embeddings (`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 (`float`, *optional*, defaults to 0.02):
            The standard deviation of the truncated_normal_initializer for initializing all weight matrices.
        encoder_layerdrop: (`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: (`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 (`bool`, *optional*, defaults to `False`):
            Scale embeddings by diving by sqrt(d_model).
        use_cache (`bool`, *optional*, defaults to `True`):
            Whether or not the model should return the last key/values attentions (not used by all models).
        num_labels: (`int`, *optional*, defaults to 3):
            The number of labels to use in [`BartForSequenceClassification`].
        forced_eos_token_id (`int`, *optional*, defaults to 2):
            The id of the token to force as the last generated token when `max_length` is reached. Usually set to
            `eos_token_id`.
    Example:
    ```python
    >>> 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 = "Deltalm"
    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=250001,
        max_position_embeddings=1024,
        encoder_layers=12,
        encoder_ffn_dim=3072,
        encoder_attention_heads=12,
        decoder_layers=6,
        decoder_ffn_dim=3072,
        decoder_attention_heads=12,
        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=0,
        forced_eos_token_id=2,
        label_smoothing=0.1,
        length_penalty=1.0,
        encoder_normalize_before=False,
        **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
        self.label_smoothing = label_smoothing
        self.encoder_normalize_before = encoder_normalize_before

        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,
            length_penalty=length_penalty,
            **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
            warnings.warn(
                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."
            )

    @property
    def num_attention_heads(self) -> int:
        return self.encoder_attention_heads

    @property
    def hidden_size(self) -> int:
        return self.d_model