Source code for mindnlp.models.t5.t5_config

# Copyright 2022 Huawei Technologies Co., Ltd
#
# 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.
# ============================================================================
"""
T5 Model config
"""

from mindnlp.abc import PreTrainedConfig
from mindnlp.configs import HF_CONFIG_URL_BASE

__all__ = ['T5Config']

T5_SUPPORT_LIST = ["t5-small", "t5-base", "t5-large", "t5-3b", "t5-11b"]

CONFIG_ARCHIVE_MAP = {
    model: HF_CONFIG_URL_BASE.format(model) for model in T5_SUPPORT_LIST
}

[docs]class T5Config(PreTrainedConfig): """ Configuration for T5 """ pretrained_config_archive_map = CONFIG_ARCHIVE_MAP def __init__( self, vocab_size=32128, d_model=512, d_kv=64, d_ff=2048, num_layers=6, num_decoder_layers=None, num_heads=8, relative_attention_num_buckets=32, relative_attention_max_distance=128, dropout_rate=0.1, layer_norm_epsilon=1e-6, initializer_factor=1.0, feed_forward_proj="relu", is_encoder_decoder=True, use_cache=True, pad_token_id=0, eos_token_id=1, **kwargs ): self.vocab_size = vocab_size self.d_model = d_model self.d_kv = d_kv self.d_ff = d_ff self.num_layers = num_layers self.num_decoder_layers = ( num_decoder_layers if num_decoder_layers is not None else self.num_layers ) # default = symmetry self.num_heads = num_heads self.relative_attention_num_buckets = relative_attention_num_buckets self.relative_attention_max_distance = relative_attention_max_distance self.dropout_rate = dropout_rate self.layer_norm_epsilon = layer_norm_epsilon self.initializer_factor = initializer_factor self.feed_forward_proj = feed_forward_proj self.use_cache = use_cache act_info = self.feed_forward_proj.split("-") self.dense_act_fn = act_info[-1] self.is_gated_act = act_info[0] == "gated" if len(act_info) > 1 and act_info[0] != "gated" or len(act_info) > 2: raise ValueError( f"`feed_forward_proj`: {feed_forward_proj} is not a valid activation function of the dense layer." "Please make sure `feed_forward_proj` is of the format `gated-{ACT_FN}` or `{ACT_FN}`, e.g. " "'gated-gelu' or 'relu'" ) # for backwards compatibility if feed_forward_proj == "gated-gelu": self.dense_act_fn = "gelu_new" super().__init__( pad_token_id=pad_token_id, eos_token_id=eos_token_id, is_encoder_decoder=is_encoder_decoder, **kwargs, )