model_config.py

# Copyright 2020 The HuggingFace Inc. team.
# Copyright (c) 2018, NVIDIA CORPORATION.  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.

import copy

from transformers.configuration_utils import PretrainedConfig
from transformers import BertConfig, EncoderDecoderConfig
from transformers.utils import logging


logger = logging.get_logger(__name__)

class DecoderInvertTextNormalizationConfig(BertConfig):
    def __init__(self, pad_token_id=1, bos_token_id=0, eos_token_id=2, **kwargs):
        super().__init__(pad_token_id=pad_token_id, bos_token_id=bos_token_id, eos_token_id=eos_token_id, **kwargs)
        self.num_hidden_layers=2


class InvertTextNormalizationConfig(EncoderDecoderConfig):
    is_composition = True
    model_type = "invert_text_normalization"
    
    def __init__(self, **kwargs):
        super().__init__(**kwargs)
        # assert (
        #     "encoder" in kwargs and "decoder" in kwargs
        # ), "Config has to be initialized with encoder and decoder config"
    #     encoder_config = kwargs.pop("encoder")
    #     encoder_model_type = encoder_config.pop("model_type")
    #     decoder_config = kwargs.pop("decoder")
    #     decoder_model_type = decoder_config.pop("model_type")

    #     from transformers.models.auto.configuration_auto import AutoConfig

    #     self.encoder = AutoConfig.for_model(encoder_model_type, **encoder_config)
    #     self.decoder = AutoConfig.for_model(decoder_model_type, **decoder_config)
    #     self.is_encoder_decoder = True

    # @classmethod
    # def from_encoder_decoder_configs(
    #     cls, encoder_config: PretrainedConfig, decoder_config: PretrainedConfig, **kwargs
    # ) -> PretrainedConfig:
    #     r"""
    #     Instantiate a :class:`~transformers.EncoderDecoderConfig` (or a derived class) from a pre-trained encoder model
    #     configuration and decoder model configuration.

    #     Returns:
    #         :class:`EncoderDecoderConfig`: An instance of a configuration object
    #     """
    #     logger.info("Set `config.is_decoder=True` and `config.add_cross_attention=True` for decoder_config")
    #     decoder_config.is_decoder = True
    #     decoder_config.add_cross_attention = True

    #     return cls(encoder=encoder_config.to_dict(), decoder=decoder_config.to_dict(), **kwargs)

    # def to_dict(self):
    #     """
    #     Serializes this instance to a Python dictionary. Override the default `to_dict()` from `PretrainedConfig`.

    #     Returns:
    #         :obj:`Dict[str, any]`: Dictionary of all the attributes that make up this configuration instance,
    #     """
    #     output = copy.deepcopy(self.__dict__)
    #     output["encoder"] = self.encoder.to_dict()
    #     output["decoder"] = self.decoder.to_dict()
    #     output["model_type"] = self.__class__.model_type
    #     return output